© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71665
    Prev
    Next
    INDEX
    Explanations

    Technical or code context

    np_max-act-logits · 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
     disambiguazione
    -0.63
    
    -0.59
    MessageOf
    -0.58
    :✨
    -0.55
    Бахар
    -0.54
    Cyfeiriadau
    -0.54
     betweenstory
    -0.52
    withIdentifier
    -0.52
    DbType
    -0.51
    oggle
    -0.48
    POSITIVE LOGITS
    jspx
    0.57
    \{\\
    0.51
     Zelt
    0.50
    ArgumentParser
    0.50
     Ringer
    0.49
     SPO
    0.47
     TAYLOR
    0.47
     étrangères
    0.46
    terms
    0.46
     rhiz
    0.46
    Activations Density 0.004%

    No Known Activations