© 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. 5-CLT-HP
    7. 1133
    Prev
    Next
    INDEX
    Explanations

    true/false questions

    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
    YES
    -0.42
     aceptas
    -0.39
    WAU
    -0.38
     me
    -0.37
    habhar
    -0.37
     secondary
    -0.37
    bigliamento
    -0.36
    wheeler
    -0.36
     over
    -0.36
    inobu
    -0.35
    POSITIVE LOGITS
     الحره
    0.87
     وتسجيلات
    0.74
     مشين
    0.67
    RenderAtEndOf
    0.67
     GIPHY
    0.65
     HasFactory
    0.64
    middels
    0.64
     كومونز
    0.63
     ModelExpression
    0.62
     للمعارف
    0.62
    Activations Density 0.006%

    No Known Activations