Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11250
    Prev
    Next
    INDEX
    Explanations

    excerpts from various texts

    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
     itſelf
    -0.82
     myſelf
    -0.79
     themſelves
    -0.77
    WebVitals
    -0.76
     ſche
    -0.75
    RenderAtEndOf
    -0.73
     étan
    -0.72
     purpoſe
    -0.71
     uſ
    -0.70
     africains
    -0.69
    POSITIVE LOGITS
     a
    0.83
     to
    0.79
     of
    0.73
     “
    0.73
     the
    0.73
     he
    0.73
     in
    0.71
     an
    0.68
     for
    0.67
     on
    0.66
    Activations Density 0.003%

    No Known Activations