© 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. 40670
    Prev
    Next
    INDEX
    Explanations

    time references

    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
     Wikiseite
    -0.56
     sidste
    -0.50
     final
    -0.50
     felicità
    -0.49
     first
    -0.49
     précédente
    -0.49
     last
    -0.48
     suivante
    -0.46
     första
    -0.45
     faibles
    -0.45
    POSITIVE LOGITS
     Мексичка
    0.87
    ⓧ
    0.77
     Administrativna
    0.75
    ThroughAttribute
    0.74
    存于互联网档案馆
    0.73
     AspNetCore
    0.73
    Diweddarwch
    0.71
     שוליים
    0.70
    KommentareTeilen
    0.69
     intptr
    0.69
    Activations Density 0.054%

    No Known Activations