© 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. 77993
    Prev
    Next
    INDEX
    Explanations

    non-English 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
    Not in Any Lists

    No Comments

    Negative Logits
    InputBorder
    -0.59
    PhysRev
    -0.50
    OSD
    -0.46
     OFDb
    -0.45
     Hannibal
    -0.44
     hwnd
    -0.44
    ]--;
    -0.43
    cipar
    -0.42
     USDA
    -0.42
    ristor
    -0.42
    POSITIVE LOGITS
     فريبيس
    0.82
    脚注の使い方
    0.66
     disambiguazione
    0.63
     nationales
    0.60
    tır
    0.59
     تانيه
    0.59
     nazionali
    0.56
     désolés
    0.56
    zetek
    0.53
    hoeddwyd
    0.52
    Activations Density 0.001%

    No Known Activations