© 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. 8958
    Prev
    Next
    INDEX
    Explanations

    distress

    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
     Davies
    -0.65
    e
    -0.63
     nhàng
    -0.60
    ta
    -0.57
    back
    -0.49
    house
    -0.49
    m
    -0.48
    sos
    -0.48
    CardHeader
    -0.47
    ing
    -0.47
    POSITIVE LOGITS
    
    0.75
    uxxxx
    0.73
    .}~\
    0.72
    ziasztok
    0.69
     становника
    0.67
    })));
    0.66
    saraba
    0.66
    :✨
    0.66
     propOrder
    0.66
    __':
    0.66
    Activations Density 0.016%

    No Known Activations