© 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. 45081
    Prev
    Next
    INDEX
    Explanations

    tham

    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
    tvguidetime
    -0.91
     esternos
    -0.82
     betweenstory
    -0.73
    GEBURTSDATUM
    -0.73
     oprot
    -0.70
    Personensuche
    -0.65
    ECE
    -0.62
     tartalomajánló
    -0.61
     Biôgrafia
    -0.61
    tham
    -0.60
    POSITIVE LOGITS
    مك
    0.52
     الرخصة
    0.52
    ""}
    0.48
     Hoek
    0.48
    i
    0.47
    ensitive
    0.47
     inimes
    0.47
     الاطلاع
    0.47
     Ginn
    0.46
    omenclature
    0.46
    Activations Density 0.088%

    No Known Activations