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. 22-CLT-HP
    4. 74259
    Prev
    Next
    INDEX
    Explanations

    technical/tool context

    np_max-act-logits · 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
    Tool
    -0.87
     chrétiens
    -0.83
     Tool
    -0.81
    Song
    -0.80
    church
    -0.79
    Word
    -0.79
    tool
    -0.79
    word
    -0.78
    law
    -0.77
     réfugiés
    -0.77
    POSITIVE LOGITS
     跳转至
    0.43
     désolés
    0.42
    DoubleQuotes
    0.38
     الرخصة
    0.37
    ▻
    0.36
    SerializedSize
    0.36
    closedir
    0.35
    setViewportView
    0.35
     distanciation
    0.35
    oling
    0.33
    Activations Density 0.018%

    No Known Activations