© 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. 243
    Prev
    Next
    INDEX
    Explanations

    instances of programming language constructs or syntax related to policies or procedures

    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
    ↵
    -0.45
    1
    -0.41
      
    -0.40
    2
    -0.37
                                   
    -0.35
    ↵↵
    -0.35
    0
    -0.35
    In
    -0.35
    app
    -0.35
     lieux
    -0.35
    POSITIVE LOGITS
     MainAxisSize
    0.84
    ImageContext
    0.82
     wireType
    0.80
     témoig
    0.80
     كومونز
    0.79
    aarrggbb
    0.77
     zwiſchen
    0.77
     queſta
    0.77
    iſchen
    0.75
    majánló
    0.75
    Activations Density 2.113%

    No Known Activations