© 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. 4-CLT-HP
    7. 3286
    Prev
    Next
    INDEX
    Explanations

    articles/pronouns

    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
     betweenstory
    -0.72
    <bos>
    -0.57
    CreateModel
    -0.51
     ModelExpression
    -0.49
    ActionMode
    -0.48
    OGND
    -0.47
    ridine
    -0.47
    enumi
    -0.46
    ios
    -0.46
    Released
    -0.45
    POSITIVE LOGITS
    uarga
    0.60
     tweet
    0.54
    ulemon
    0.51
    Bronnen
    0.51
     Tweet
    0.51
    kasten
    0.50
    icating
    0.49
     مرئيه
    0.48
    iastes
    0.48
    PRNewswire
    0.48
    Activations Density 0.016%

    No Known Activations