© 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. 5-CLT-HP
    7. 4600
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ?
    -0.35
     yli
    -0.32
    sequelize
    -0.31
     произ
    -0.30
     lost
    -0.30
    exempt
    -0.29
    ?_
    -0.29
    ’
    -0.29
     performed
    -0.29
     competed
    -0.29
    POSITIVE LOGITS
     Efq
    0.94
     تضيفلها
    0.93
    
    0.90
     متعلقه
    0.88
    MigrationBuilder
    0.87
     通販
    0.86
     itſelf
    0.84
    expandindo
    0.84
    IndentedString
    0.84
    Personensuche
    0.83
    Activations Density 0.007%

    No Known Activations