© 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. 5-CLT-HP
    7. 95246
    Prev
    Next
    INDEX
    Explanations

    have/be

    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
    
    -0.71
    lex
    -0.47
    ęp
    -0.44
    veira
    -0.43
     odst
    -0.43
     nito
    -0.42
    getVar
    -0.41
    toast
    -0.41
     voids
    -0.41
     ned
    -0.40
    POSITIVE LOGITS
    RenderAtEndOf
    1.05
    __).
    0.77
    WebServlet
    0.75
     AssemblyCulture
    0.71
    WireFormatLite
    0.70
     ModelExpression
    0.68
    %");
    0.66
     raiſ
    0.66
    LookAnd
    0.65
     تانيه
    0.65
    Activations Density 0.003%

    No Known Activations