© 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. 5-CLT-HP
    7. 1011
    Prev
    Next
    INDEX
    Explanations

    list

    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
    Personensuche
    -0.83
    transQ
    -0.69
    ScopeManager
    -0.66
    tvguidetime
    -0.64
    RegressionTest
    -0.63
    StructEnd
    -0.63
    Chham
    -0.63
    таратура
    -0.62
    Autoritní
    -0.61
     незавершена
    -0.60
    POSITIVE LOGITS
     Audiodateien
    0.61
    rungsseite
    0.49
    :`
    0.49
    !!:
    0.47
    }>;
    0.47
    soort
    0.47
    .`
    0.46
    chures
    0.46
    anians
    0.45
    ).]
    0.45
    Activations Density 0.003%

    No Known Activations