© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93380
    Prev
    Next
    INDEX
    Explanations

    emic

    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
    ate
    -1.45
    ATE
    -0.94
    sets
    -0.82
    sed
    -0.76
    ving
    -0.75
    ale
    -0.67
    cian
    -0.67
    ist
    -0.66
    ates
    -0.66
    es
    -0.66
    POSITIVE LOGITS
    autique
    0.66
    transQ
    0.65
    GEBURTSDATUM
    0.63
    MigrationBuilder
    0.63
    pholes
    0.62
    operatively
    0.62
    ranza
    0.61
    Abitanti
    0.61
    anhänger
    0.61
    InstrumentedTest
    0.61
    Activations Density 0.093%

    No Known Activations