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. 74600
    Prev
    Next
    INDEX
    Explanations

    for (in many languages)

    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
    MergeFrom
    -0.50
    ?}",
    -0.48
    Зноскі
    -0.47
     Italijani
    -0.46
     Protection
    -0.45
     跳转至
    -0.45
    abank
    -0.44
    pidou
    -0.44
    ناء
    -0.44
     Hygiene
    -0.43
    POSITIVE LOGITS
     for
    1.84
    for
    1.73
     For
    1.42
    For
    1.41
     FOR
    1.34
    FOR
    1.16
     для
    1.15
     voor
    0.99
     untuk
    0.97
     für
    0.96
    Activations Density 0.008%

    No Known Activations