© 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. 20-CLT-HP
    7. 72307
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    UrlResolution
    -0.83
    findpost
    -0.77
     كومونز
    -0.63
    msgTypes
    -0.60
     resourceCulture
    -0.58
    wpi
    -0.57
     esternos
    -0.54
     Paglinawan
    -0.53
    InitVars
    -0.53
    DispatchToProps
    -0.53
    POSITIVE LOGITS
    demia
    0.57
    CloseOperation
    0.54
     relâche
    0.53
    étranger
    0.50
    abia
    0.49
     setCode
    0.48
     fig
    0.48
    ujących
    0.48
     echa
    0.46
     fidélité
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.