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. 0-CLT-HP
    4. 40839
    Prev
    Next
    INDEX
    Explanations

    dimensional

    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
     defaultstate
    -0.74
     leçons
    -0.74
     الاطلاع
    -0.73
     enfans
    -0.72
     modalités
    -0.71
     prisonniers
    -0.71
     prochaines
    -0.69
     leçon
    -0.69
     journaux
    -0.68
     dégâts
    -0.68
    POSITIVE LOGITS
    ers
    0.54
    ed
    0.50
    ized
    0.48
    ery
    0.48
    ish
    0.48
    ert
    0.47
     Hindu
    0.47
    we
    0.46
     fan
    0.46
    ray
    0.46
    Activations Density 0.151%

    No Known Activations