© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97098
    Prev
    Next
    INDEX
    Explanations

    error logs/programming

    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
     discharges
    -0.72
     discharged
    -0.50
     bờ
    -0.50
     of
    -0.49
    LATE
    -0.48
     co
    -0.48
     spit
    -0.48
     kum
    -0.47
    dorff
    -0.47
     cul
    -0.46
    POSITIVE LOGITS
     ModelExpression
    0.90
    Datuak
    0.78
     générations
    0.77
     ostavi
    0.76
     aikaa
    0.75
     tartalomajánló
    0.74
     varandra
    0.73
     dieux
    0.73
     uova
    0.70
     auroit
    0.70
    Activations Density 0.195%

    No Known Activations