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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 2016
    Prev
    Next
    INDEX
    Explanations

    explains

    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
     explains
    -0.94
     Explains
    -0.85
     مشين
    -0.80
     برانيه
    -0.77
    ]**
    -0.74
    AnimationsModule
    -0.72
     nahilalakip
    -0.71
    Bakgrunnsstoff
    -0.71
     חיצוניים
    -0.71
     explique
    -0.69
    POSITIVE LOGITS
     what
    0.79
     how
    0.75
     that
    0.70
    ,
    0.66
     the
    0.64
     by
    0.61
    .
    0.61
     where
    0.60
     and
    0.57
     it
    0.56
    Activations Density 0.742%

    No Known Activations