© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15657
    Prev
    Next
    INDEX
    Explanations

    questions and tasks

    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
    Colour
    -0.80
     recognising
    -0.78
    Ещё
    -0.77
    colour
    -0.77
     utilising
    -0.77
    colours
    -0.76
     optimise
    -0.75
     optimisation
    -0.75
     учё
    -0.75
     realising
    -0.73
    POSITIVE LOGITS
     InputDecoration
    0.55
    ubin
    0.51
     rotten
    0.50
    InsertCommand
    0.49
    migrationBuilder
    0.49
     ostavi
    0.49
    awtextra
    0.47
    extendable
    0.47
    BeginContext
    0.47
    цездатний
    0.46
    Activations Density 0.007%

    No Known Activations