© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76087
    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
     незавершена
    -0.87
    //</
    -0.71
     occafion
    -0.71
    awtextra
    -0.63
    /*:
    -0.63
     nahilalakip
    -0.62
    Gweler
    -0.61
     Roskov
    -0.60
    interopRequire
    -0.60
    basicConfig
    -0.60
    POSITIVE LOGITS
    ROW
    0.52
    zones
    0.45
    zone
    0.45
    Zone
    0.44
    rones
    0.43
    NR
    0.42
     Band
    0.42
     Zone
    0.42
    ROWS
    0.40
     Zones
    0.40
    Activations Density 0.000%

    No Known Activations