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. 6
    Prev
    Next
    INDEX
    Explanations

    computer code/URLs

    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
    脚注の使い方
    -1.14
     '\\;'
    -1.07
    AddTagHelper
    -1.05
     itſelf
    -1.05
    numerusform
    -1.04
    Бахар
    -1.04
     myſelf
    -1.04
    ")));
    
    -1.03
    aarrggbb
    -1.01
     Meksiku
    -1.00
    POSITIVE LOGITS
    -
    0.57
    '
    0.56
     to
    0.55
     
    0.54
     \
    0.53
     the
    0.53
    ’
    0.52
    .
    0.51
     …
    0.49
    /
    0.49
    Activations Density 2.557%

    No Known Activations