© 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. 10345
    Prev
    Next
    INDEX
    Explanations

    prior

    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
    __*/
    -0.48
     ball
    -0.42
     būtų
    -0.40
    ázaro
    -0.39
     scoper
    -0.38
     songs
    -0.38
    CustomerId
    -0.38
     consommate
    -0.38
    ptime
    -0.38
    тору
    -0.38
    POSITIVE LOGITS
    windowFixed
    0.90
    principalColumn
    0.82
    Personensuche
    0.80
     Paglinawan
    0.76
     Vikipedi
    0.76
    ⓧ
    0.75
     للاسماء
    0.73
     pinulongan
    0.71
    localctx
    0.71
     <=",
    0.68
    Activations Density 0.069%

    No Known Activations