© 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. 39959
    Prev
    Next
    INDEX
    Explanations

    interventions

    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
     }{@
    -0.88
     estekak
    -0.76
    tvguidetime
    -0.75
    脚注の使い方
    -0.72
    InstrumentedTest
    -0.69
     ContentValues
    -0.68
    Xna
    -0.68
     MainAxisSize
    -0.68
    GEBURTSDATUM
    -0.67
     فريبيس
    -0.65
    POSITIVE LOGITS
    ing
    0.97
    t
    0.63
    n
    0.59
    er
    0.56
    en
    0.53
    ingen
    0.53
    o
    0.50
    ted
    0.50
    char
    0.48
    y
    0.47
    Activations Density 0.112%

    No Known Activations