© 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. 12317
    Prev
    Next
    INDEX
    Explanations

    quantity

    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
    RenderAtEndOf
    -0.76
    usercontent
    -0.58
    IntoConstraints
    -0.50
     kaynağından
    -0.49
     فريبيس
    -0.47
    ++]
    -0.46
    dom
    -0.44
     rid
    -0.44
     material
    -0.42
    CPtr
    -0.41
    POSITIVE LOGITS
    exitRule
    0.68
    MENAFN
    0.67
    TestTools
    0.60
    ntö
    0.60
     essais
    0.60
     ?>/
    0.59
    Newspaper
    0.59
    structors
    0.58
     समीक्षक
    0.58
     honte
    0.56
    Activations Density 0.007%

    No Known Activations