© 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. 71525
    Prev
    Next
    INDEX
    Explanations

    Code or programming text

    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
     when
    -1.06
     quando
    -0.93
    when
    -0.88
     когда
    -0.82
     cuando
    -0.82
    When
    -0.80
     When
    -0.74
    quando
    -0.73
     WHEN
    -0.73
     عندما
    -0.70
    POSITIVE LOGITS
    saraba
    0.60
    AddTagHelper
    0.59
    
    0.53
     utafitiHapana
    0.52
     während
    0.49
     for
    0.49
     berk
    0.49
    BoxLayout
    0.49
    下载附件
    0.49
    脚注の使い方
    0.49
    Activations Density 0.000%

    No Known Activations