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. 5
    Prev
    Next
    INDEX
    Explanations

    ne

    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
    ne
    -0.95
    ti
    -0.65
    n
    -0.63
    uter
    -0.62
    te
    -0.61
    н
    -0.54
    s
    -0.53
    z
    -0.51
    k
    -0.47
    ties
    -0.46
    POSITIVE LOGITS
    клопе
    0.84
    ьаж
    0.73
    ⓧ
    0.70
     समीक्षाओं
    0.69
    ViewImports
    0.68
     &___
    0.68
    лтемелер
    0.65
    
    0.65
     mukana
    0.65
    帖最后由
    0.65
    Activations Density 0.812%

    No Known Activations