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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43856
    Prev
    Next
    INDEX
    Explanations

    Labels

    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
     labels
    -0.82
    labels
    -0.81
     Labels
    -0.81
    Labels
    -0.79
    weds
    -0.75
     landmarks
    -0.66
    erun
    -0.65
     oreille
    -0.64
     وتسجيلات
    -0.63
    topes
    -0.63
    POSITIVE LOGITS
    endregion
    0.52
     pageable
    0.49
    contentValues
    0.48
    typeorm
    0.47
    prepareStatement
    0.46
    BooleanField
    0.46
    πως
    0.45
    öner
    0.45
     resultCode
    0.45
    abito
    0.44
    Activations Density 0.157%

    No Known Activations