© 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. 403
    Prev
    Next
    INDEX
    Explanations

    sum

    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
    Sum
    -0.86
    SUM
    -0.85
     SUM
    -0.83
     Sum
    -0.81
    sum
    -0.79
     sum
    -0.78
     summing
    -0.56
     gyhoeddwyd
    -0.54
     sums
    -0.54
    Lähteet
    -0.51
    POSITIVE LOGITS
     فريبيس
    0.66
    PerformLayout
    0.60
    maries
    0.59
    nologies
    0.56
     cols
    0.56
     dirs
    0.55
     تضيفلها
    0.55
    tôi
    0.55
    wieś
    0.54
    mary
    0.54
    Activations Density 0.050%

    No Known Activations