© 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. 465
    Prev
    Next
    INDEX
    Explanations

    health

    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
    idoo
    -0.53
    panes
    -0.46
    dominal
    -0.45
    oner
    -0.40
    als
    -0.40
    stander
    -0.39
    ous
    -0.39
    ing
    -0.39
    ColumnHeaders
    -0.38
    ener
    -0.38
    POSITIVE LOGITS
     Office
    0.69
     Invention
    0.69
    complexType
    0.68
     Legislation
    0.66
    SequentialGroup
    0.64
    gdx
    0.63
     Phrase
    0.63
     Outbreak
    0.62
     Appeals
    0.62
    DotNetBar
    0.62
    Activations Density 0.042%

    No Known Activations