© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95073
    Prev
    Next
    INDEX
    Explanations

    so

    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
    <bos>
    -1.09
    /*
    -0.90
    twimg
    -0.88
    #+#
    -0.85
    colgroup
    -0.80
     հղումներ
    -0.77
    WritableDatabase
    -0.75
     فريبيس
    -0.73
    InjectAttribute
    -0.72
    ,:);
    -0.72
    POSITIVE LOGITS
    ogna
    0.42
    Far
    0.42
    jauh
    0.40
     far
    0.40
     term
    0.39
    ági
    0.38
    届
    0.37
     Far
    0.37
    TSD
    0.36
     relatie
    0.36
    Activations Density 0.007%

    No Known Activations