© 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. 95249
    Prev
    Next
    INDEX
    Explanations

    code excerpts

    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>
    -0.90
     ModelExpression
    -0.71
     تضيفلها
    -0.53
    oplayer
    -0.53
     Paglinawan
    -0.51
    DockStyle
    -0.50
    oredCriteria
    -0.49
     Limb
    -0.47
    EndInit
    -0.47
     Tox
    -0.47
    POSITIVE LOGITS
    LabelTagHelper
    0.54
    iterranean
    0.52
    tvguidetime
    0.50
    poshmark
    0.50
    )_/¯
    0.48
    arxiv
    0.48
    //-->
    0.47
    bandcamp
    0.46
    twimg
    0.46
    Дереккөздер
    0.46
    Activations Density 0.093%

    No Known Activations