© 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. 15
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and syntax used in formal proofs and equations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.73
    
    -0.72
     useAppContext
    -0.67
     arşivlendi
    -0.63
    waitKey
    -0.63
    principalTable
    -0.62
    دانشنامهٔ
    -0.61
    ContentLoaded
    -0.60
    󠁴
    -0.60
    CloseOperation
    -0.60
    POSITIVE LOGITS
     enfans
    0.40
     faptul
    0.38
       
    0.37
    httphttps
    0.37
           
    0.36
     Савезне
    0.36
          
    0.36
    icznie
    0.35
    <u>
    0.34
    Kolkata
    0.34
    Activations Density 9.223%

    No Known Activations