© 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. 1-CLT-HP
    7. 45635
    Prev
    Next
    INDEX
    Explanations

    ulos

    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
    ulose
    -0.78
    WebElementEntity
    -0.76
     EconPapers
    -0.73
     Sylvia
    -0.67
    DeleteBehavior
    -0.66
    ValueStyle
    -0.64
     mergeFrom
    -0.63
    UnusedPrivate
    -0.61
    Sylvia
    -0.61
    IsContent
    -0.61
    POSITIVE LOGITS
    sities
    0.70
    uldade
    0.63
    sitis
    0.60
    ality
    0.57
    tivities
    0.50
     continuity
    0.50
    Aber
    0.49
     spro
    0.49
    IONS
    0.48
    urch
    0.48
    Activations Density 0.009%

    No Known Activations