© 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. 95018
    Prev
    Next
    INDEX
    Explanations

    Legal/regulatory documents

    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
    存于互联网档案馆
    -0.60
    <i>
    -0.54
    <blockquote>
    -0.52
    <em>
    -0.52
    }{*}{}
    -0.50
    tvguidetime
    -0.49
    Ő
    -0.49
    '%(
    -0.48
    ''
    -0.47
    $).
    -0.47
    POSITIVE LOGITS
    XmlAccessType
    0.71
    WebVitals
    0.71
     
    0.63
     GeoNames
    0.59
     ModelExpression
    0.58
    extAlignment
    0.57
    AndEndTag
    0.57
     Italijanski
    0.54
     دیکھیے
    0.54
    InSection
    0.52
    Activations Density 0.010%

    No Known Activations