© 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. 0-CLT-HP
    7. 39982
    Prev
    Next
    INDEX
    Explanations

    these

    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
    johtaja
    -0.46
    curacy
    -0.46
    getLatitude
    -0.45
    kurang
    -0.44
    kredit
    -0.42
    AnimationsModule
    -0.42
    ragalactic
    -0.42
     vuotta
    -0.41
     Whistle
    -0.41
    coration
    -0.40
    POSITIVE LOGITS
    MigrationBuilder
    0.88
    migrationBuilder
    0.78
    parsedMessage
    0.73
    </s>
    0.72
    UnusedPrivate
    0.69
    InjectAttribute
    0.68
    UnsafeEnabled
    0.66
     '.
    0.65
     ".
    0.64
    )".
    0.64
    Activations Density 0.054%

    No Known Activations