© 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. 282
    Prev
    Next
    INDEX
    Explanations

    mathematical constructs and formal definitions in text

    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
    GEBURTSDATUM
    -0.82
    oredCriteria
    -0.73
    tonode
    -0.69
    ftagPool
    -0.68
     Obrador
    -0.66
     ProtoMessage
    -0.64
    MessageOf
    -0.61
    .*")]
    -0.61
    EDEFAULT
    -0.60
     lenker
    -0.59
    POSITIVE LOGITS
     and
    0.37
     Ful
    0.36
    entityId
    0.35
    Ind
    0.35
    思わず
    0.33
     chart
    0.33
     Ind
    0.33
    nextProps
    0.33
    仕方
    0.32
     put
    0.32
    Activations Density 2.333%

    No Known Activations