In the image, 20 feature maps the network has learned, each devoted to a feature. Each map is a matrix 5X5 of weights: the darker the colour, the heavier the weight there, which implies a stronger response of the network on the input image region at that location. The maps clearly shows the network has learned graphical patterns, for example in the third one on the top row, there is a vertical bar top right. What features a CNN actually learn isn't a trivial thing to ascertain, as in, the networks learns to recognise patterns on its own, but it's non trivial to imagine which ones beforehand. That's their power.