© 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. 436
    Prev
    Next
    INDEX
    Explanations

    a

    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
    IsContent
    -0.61
    <bos>
    -0.60
    createTextNode
    -0.55
    agisse
    -0.54
    المكان
    -0.54
    SaveChangesAsync
    -0.54
    runApp
    -0.53
    ServletException
    -0.53
     ſtate
    -0.53
     melange
    -0.52
    POSITIVE LOGITS
     Other
    0.54
    AndEndTag
    0.52
     OTHER
    0.48
     andra
    0.48
    cier
    0.48
     ADVANCED
    0.48
    example
    0.48
    ,
    0.46
    </thead>
    0.46
    ishment
    0.46
    Activations Density 0.017%

    No Known Activations