© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4526
    Prev
    Next
    INDEX
    Explanations

    punctuation/separators

    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
     Sometimes
    -0.50
     Some
    -0.47
    Other
    -0.46
     Certain
    -0.46
    Sometimes
    -0.46
    and
    -0.46
    other
    -0.46
     Anything
    -0.45
     Other
    -0.45
    Some
    -0.44
    POSITIVE LOGITS
    出版年
    0.82
    ]")]
    0.81
    tagHelperRunner
    0.78
    Rüyada
    0.77
    WEBPACK
    0.77
    ConstraintMaker
    0.77
    QMetaType
    0.77
    MigrationBuilder
    0.75
    stolic
    0.73
    mapStateToProps
    0.73
    Activations Density 0.007%

    No Known Activations