© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77923
    Prev
    Next
    INDEX
    Explanations

    Computer code and foreign languages

    np_max-act-logits · 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
    AllowUser
    -0.57
     mer
    -0.54
     n
    -0.53
     plated
    -0.52
    IDENTAL
    -0.52
    rrggbb
    -0.51
     ((((
    -0.51
     roll
    -0.51
    :✨
    -0.50
     cop
    -0.50
    POSITIVE LOGITS
    AnchorStyles
    0.56
    ckså
    0.53
    parsedMessage
    0.52
     لينك
    0.52
     szár
    0.50
    رشف
    0.50
    клопе
    0.49
    HAC
    0.48
     hinaus
    0.45
     Chaves
    0.45
    Activations Density 0.000%

    No Known Activations