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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3339
    Prev
    Next
    INDEX
    Explanations

    legal document extracts

    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
     that
    -0.92
     she
    -0.69
     always
    -0.68
     where
    -0.68
     coming
    -0.66
     they
    -0.65
     who
    -0.65
    that
    -0.65
     which
    -0.64
     should
    -0.64
    POSITIVE LOGITS
    Rüyada
    0.53
     bénévoles
    0.49
     négociations
    0.49
    VersionUID
    0.48
     réfrig
    0.48
     vaisseaux
    0.48
     enfans
    0.47
     numéros
    0.46
    }\]
    0.46
     prêtres
    0.45
    Activations Density 0.006%

    No Known Activations