© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 879
    Prev
    Next
    INDEX
    Explanations

    diet and health

    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
    <bos>
    -0.68
     ๆ
    -0.52
     den
    -0.48
    ๆ
    -0.47
    laufen
    -0.46
    uxxxx
    -0.45
    mell
    -0.45
    </b>
    -0.44
    ード
    -0.43
    );\
    -0.42
    POSITIVE LOGITS
     Houſe
    0.77
     itſelf
    0.75
     Reſ
    0.73
     Majefty
    0.69
     sherds
    0.68
    يكب
    0.68
     ſy
    0.68
     ſhe
    0.68
     pleaſure
    0.68
     ſtand
    0.67
    Activations Density 0.019%

    No Known Activations