© 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. 0-CLT-HP
    7. 95550
    Prev
    Next
    INDEX
    Explanations

    stories

    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
     message
    -0.89
     ghost
    -0.87
     gross
    -0.85
     Message
    -0.85
    Message
    -0.74
     Sk
    -0.71
    message
    -0.70
     Ghost
    -0.70
     ghosts
    -0.68
    gross
    -0.65
    POSITIVE LOGITS
    mybatisplus
    0.84
    twimg
    0.79
    AccessorTable
    0.74
    enterOuterAlt
    0.67
    :✨
    0.66
    yntaxException
    0.66
    ConstraintMaker
    0.66
    SequentialGroup
    0.64
    __':
    0.64
    letoe
    0.64
    Activations Density 1.610%

    No Known Activations