© 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. 39956
    Prev
    Next
    INDEX
    Explanations

    benefits

    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
     benefits
    -1.22
    benefits
    -0.96
     advantages
    -0.88
     benefit
    -0.85
     Benefits
    -0.83
    Benefits
    -0.82
     BENEFITS
    -0.81
     EconPapers
    -0.80
     HasFactory
    -0.79
    RenderAtEndOf
    -0.79
    POSITIVE LOGITS
     for
    0.67
    .
    0.63
     and
    0.56
    ,
    0.56
     in
    0.55
     like
    0.54
     from
    0.52
     upon
    0.50
     didik
    0.49
     to
    0.49
    Activations Density 0.016%

    No Known Activations