© 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. 5-CLT-HP
    7. 6093
    Prev
    Next
    INDEX
    Explanations

    all

    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
    Negative Logits
    WriteTagHelper
    -0.72
    +#+#
    -0.60
     handleMessage
    -0.60
    BagConstraints
    -0.59
    jspx
    -0.59
     Numerade
    -0.58
    SBATCH
    -0.58
    脚注の使い方
    -0.57
     CURIAM
    -0.56
    mybatisplus
    -0.55
    POSITIVE LOGITS
    Примечания
    0.56
     aDecoder
    0.52
    ILERS
    0.50
    tillos
    0.48
     end
    0.48
    ymce
    0.47
     Ago
    0.47
     Schlag
    0.46
     beginnen
    0.44
    ENDS
    0.44
    Activations Density 0.005%

    No Known Activations