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. 40850
    Prev
    Next
    INDEX
    Explanations

    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
    ConstraintMaker
    -0.91
    脚注の使い方
    -0.81
    +#+#
    -0.77
     مشين
    -0.76
    makeConstraints
    -0.74
    TagMode
    -0.71
    CloseOperation
    -0.69
    ToBounds
    -0.65
    ReusableCell
    -0.63
    rowave
    -0.59
    POSITIVE LOGITS
    <bos>
    1.13
    ↵↵
    0.57
    <strong>
    0.47
    ال
    0.46
    У
    0.46
     mobilization
    0.43
    De
    0.43
    <em>
    0.43
    Home
    0.42
     îns
    0.42
    Activations Density 0.020%

    No Known Activations