© 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. 14474
    Prev
    Next
    INDEX
    Explanations

    Museums and locations

    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
    Билгалдахарш
    -0.65
    yarnpkg
    -0.64
    ########.
    -0.62
    __(/*!
    -0.59
    endpush
    -0.58
    dide
    -0.57
    Зноскі
    -0.55
    DeleteBehavior
    -0.55
    anded
    -0.55
     Peak
    -0.55
    POSITIVE LOGITS
    ConstraintMaker
    0.62
     Monfieur
    0.50
    errHandler
    0.49
    contentLoaded
    0.48
    WidgetItem
    0.46
    aarrggbb
    0.45
     Chriftian
    0.45
    🏽
    0.44
    blurRadius
    0.44
    🏾
    0.44
    Activations Density 0.146%

    No Known Activations