© 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. 97080
    Prev
    Next
    INDEX
    Explanations

    Forty/Fifty

    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
     fifty
    -1.05
     forty
    -0.93
     sixty
    -0.89
     Fifty
    -0.88
     seventy
    -0.85
     thirty
    -0.81
     eighty
    -0.80
     ninety
    -0.77
     cincuenta
    -0.73
     twenty
    -0.72
    POSITIVE LOGITS
     ModelExpression
    0.84
    something
    0.70
     percent
    0.68
    0
    0.66
    one
    0.63
     فريبيس
    0.60
    bewerken
    0.60
     للاسماء
    0.60
    awtextra
    0.60
    Rüyada
    0.59
    Activations Density 0.444%

    No Known Activations