© 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. 20-CLT-HP
    7. 74968
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     tra
    -0.51
    #
    -0.49
    kwds
    -0.49
    retan
    -0.49
     content
    -0.46
     Lud
    -0.46
    content
    -0.46
     honeymoon
    -0.46
     cultural
    -0.45
     Cultural
    -0.45
    POSITIVE LOGITS
     Мексичка
    0.85
    Personendaten
    0.76
    styleType
    0.73
     ویکی‌پدیای
    0.68
     Lightboxes
    0.66
     كومونز
    0.66
     FetchType
    0.66
     BitmapFactory
    0.65
     TextInputType
    0.63
     disponibilités
    0.63
    Activations Density 0.001%

    No Known Activations