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. 40879
    Prev
    Next
    INDEX
    Explanations

    ers

    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
    tvguidetime
    -0.88
     BoxDecoration
    -0.80
    :✨
    -0.76
    NameInMap
    -0.75
    adaptiveStyles
    -0.75
    IonicModule
    -0.74
    WebElementEntity
    -0.73
     Mitochond
    -0.71
     صوتيه
    -0.70
    XmlAccessorType
    -0.69
    POSITIVE LOGITS
    <bos>
    0.69
    diğinde
    0.50
    razio
    0.46
     the
    0.46
     out
    0.45
     off
    0.45
     in
    0.43
     though
    0.43
    mişti
    0.43
    ſhip
    0.42
    Activations Density 0.399%

    No Known Activations