© 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. 5-CLT-HP
    7. 6270
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    Negative Logits
    by
    -0.48
     soldati
    -0.41
     accanto
    -0.41
     juuri
    -0.41
     have
    -0.40
     lavoratori
    -0.40
     rivière
    -0.40
     are
    -0.39
    řízen
    -0.39
    Have
    -0.38
    POSITIVE LOGITS
     >=",
    0.90
    istoitu
    0.79
    }>;
    0.79
     Мексичка
    0.78
    #+#
    0.78
     BrowserModule
    0.75
     समीक्षाओं
    0.75
     *)__
    0.74
     للمعارف
    0.72
     חיצוניים
    0.71
    Activations Density 0.056%

    No Known Activations