© 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. 77936
    Prev
    Next
    INDEX
    Explanations

    model

    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
    makeConstraints
    -0.91
     disambiguazione
    -0.87
     мәкал
    -0.82
     ſaid
    -0.81
     preſent
    -0.80
    NameInMap
    -0.79
     بيها
    -0.77
    GIVEREF
    -0.75
     وتسجيلات
    -0.75
     juſ
    -0.75
    POSITIVE LOGITS
     model
    0.63
     live
    0.44
     models
    0.43
     MODEL
    0.40
     Model
    0.40
    model
    0.39
     modelo
    0.38
    模型
    0.37
     modelu
    0.36
    RTHOOK
    0.36
    Activations Density 0.000%

    No Known Activations