© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 142
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant differences or impacts related to physical or structural properties

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    </tfoot>
    -0.58
     aze
    -0.48
    Eti
    -0.48
    WSER
    -0.46
     answer
    -0.46
     Eti
    -0.45
    ForTesting
    -0.45
    dummy
    -0.45
    answer
    -0.44
     Coll
    -0.44
    POSITIVE LOGITS
     large
    0.73
     great
    0.71
     highly
    0.68
     wide
    0.67
     duża
    0.67
     very
    0.66
     intense
    0.66
     Very
    0.65
     מאוד
    0.65
     huge
    0.65
    Activations Density 3.132%

    No Known Activations