© 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. 71553
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    Negative Logits
    :✨
    -0.72
    #+#
    -0.56
     חיצוניים
    -0.50
     समीक्षाओं
    -0.49
     وتسجيلات
    -0.45
     оригіналу
    -0.44
     الحره
    -0.42
    slf
    -0.42
    Попис
    -0.41
     "..\..\
    -0.40
    POSITIVE LOGITS
    Personendaten
    0.79
    ThroughAttribute
    0.78
    AndEndTag
    0.66
    tanleria
    0.65
     ویکی‌پدی
    0.62
     JpaRepository
    0.60
    tagext
    0.57
     getItemId
    0.57
    Referências
    0.56
    ResumeLayout
    0.56
    Activations Density 0.008%

    No Known Activations