© 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. 409
    Prev
    Next
    INDEX
    Explanations

    mathematical theorems and their key components

    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
    FunctionFlags
    -0.47
     mandatario
    -0.43
    colhead
    -0.40
    <tfoot>
    -0.40
    aarrggbb
    -0.40
    Predecesor
    -0.38
    {{/
    -0.38
    routeProvider
    -0.38
     '\\;'
    -0.37
    horabuena
    -0.36
    POSITIVE LOGITS
     autorytatywna
    0.55
    Cyfarwyddwr
    0.46
     NSError
    0.45
    
    0.44
     estekak
    0.44
     Daß
    0.44
    Viungo
    0.43
     ComVisible
    0.42
     papers
    0.42
    تقاوى
    0.42
    Activations Density 3.603%

    No Known Activations