© 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. 71455
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
     Seven
    -0.94
     seventeen
    -0.88
     SEVEN
    -0.85
     seven
    -0.83
    Seven
    -0.83
     Seventeen
    -0.79
    SEVEN
    -0.78
    XVII
    -0.77
     seventh
    -0.77
     seventy
    -0.77
    POSITIVE LOGITS
     étrangers
    0.47
    fromnode
    0.47
    webElementXpaths
    0.47
    chtenstein
    0.44
     personnalité
    0.44
    
    0.44
    pyrene
    0.43
    ատ
    0.43
    礎
    0.43
     Unger
    0.43
    Activations Density 0.001%

    No Known Activations