© 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. 97209
    Prev
    Next
    INDEX
    Explanations

    disease, bacteria, and pain

    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
    confidence
    -0.73
    findpost
    -0.73
    aarrggbb
    -0.71
     betweenstory
    -0.70
    mybatisplus
    -0.69
     Confidence
    -0.69
    twimg
    -0.69
    nữ
    -0.69
    }}]{
    -0.68
    Confidence
    -0.67
    POSITIVE LOGITS
    <
    0.64
     Anſ
    0.59
     Conſ
    0.57
    I
    0.54
     Perſ
    0.52
     Diſ
    0.52
    *
    0.51
     Jefus
    0.51
     againſt
    0.50
     reaſon
    0.50
    Activations Density 0.955%

    No Known Activations