© 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. 1-CLT-HP
    7. 8667
    Prev
    Next
    INDEX
    Explanations

    Illness/disease

    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
    ьаж
    -0.79
    <bos>
    -0.78
     consultato
    -0.73
     insuffisamment
    -0.71
    enchymal
    -0.70
     nakalista
    -0.69
     становника
    -0.69
    +#+#
    -0.67
     дописавши
    -0.66
     createSlice
    -0.65
    POSITIVE LOGITS
    antd
    0.49
    vited
    0.41
     (%
    0.38
    e
    0.36
    DllImport
    0.36
    }^{+\
    0.36
    ände
    0.36
    😠
    0.35
     jeans
    0.35
    ;%
    0.35
    Activations Density 0.013%

    No Known Activations