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. 40769
    Prev
    Next
    INDEX
    Explanations

    you

    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
     you
    -0.78
    ’
    -0.66
     it
    -0.63
    '
    -0.62
     that
    -0.61
    .
    -0.60
    ,
    -0.60
     "
    -0.59
     we
    -0.59
     in
    -0.59
    POSITIVE LOGITS
    Personensuche
    1.04
    GEBURTSDATUM
    1.03
    GOTREF
    1.02
     jScrollPane
    0.96
     ་་
    0.95
    />";
    0.95
     فريبيس
    0.94
    %";
    0.94
     Forumite
    0.92
     propOrder
    0.91
    Activations Density 0.246%

    No Known Activations