© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 428
    Prev
    Next
    INDEX
    Explanations

    religion and community gatherings

    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
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.53
     pouvoirs
    -0.50
    AxisAlignment
    -0.49
    mybatisplus
    -0.49
     défauts
    -0.47
     nuages
    -0.47
     prochaines
    -0.46
    uevos
    -0.45
     abgeschlossen
    -0.45
     rayures
    -0.45
    POSITIVE LOGITS
    oredCriteria
    0.90
    webElementXpaths
    0.83
    లాలు
    0.74
     Савезне
    0.71
    Хьажоргаш
    0.71
    PreferredItem
    0.69
     regularly
    0.69
    SharedCtor
    0.66
     Drapeau
    0.60
    السكان
    0.60
    Activations Density 0.001%

    No Known Activations