© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1234
    Prev
    Next
    INDEX
    Explanations

    Excerpts from informative texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.69
     تضيفلها
    -0.62
     Biôgrafia
    -0.56
     varandra
    -0.50
     }}"></
    -0.47
     sûr
    -0.44
     lèvres
    -0.42
    ValueStyle
    -0.42
     kuin
    -0.41
    OGND
    -0.41
    POSITIVE LOGITS
     establishing
    0.61
     sterility
    0.60
     dorsal
    0.60
     priors
    0.58
     opium
    0.57
    WillAppear
    0.57
     goods
    0.56
     coefficient
    0.56
     chlorophyll
    0.55
     CFD
    0.54
    Activations Density 0.014%

    No Known Activations