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. 74571
    Prev
    Next
    INDEX
    Explanations

    Directional regions

    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
     southwestern
    -0.84
     western
    -0.82
    Western
    -0.80
     Western
    -0.79
     Southwestern
    -0.77
    western
    -0.77
     southwest
    -0.71
     WESTERN
    -0.71
    West
    -0.69
     Southwest
    -0.68
    POSITIVE LOGITS
     Northeast
    0.82
     northeast
    0.77
    Northeast
    0.66
     للاسماء
    0.65
    northeast
    0.63
     East
    0.62
     northeastern
    0.61
     nahilalakip
    0.60
     Northeastern
    0.58
    DllImport
    0.54
    Activations Density 0.037%

    No Known Activations