© 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. 384
    Prev
    Next
    INDEX
    Explanations

    code structure and formatting elements in programming or markup languages

    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
     iſt
    -0.45
     pleaſure
    -0.45
     ſch
    -0.45
     sond
    -0.44
    sellor
    -0.43
     canst
    -0.42
     viſ
    -0.42
     myſelf
    -0.42
    astify
    -0.42
     houſe
    -0.41
    POSITIVE LOGITS
    endpush
    0.90
    ɵɵelementEnd
    0.81
     مشين
    0.81
    EndContext
    0.79
    endif
    0.71
     endwhile
    0.70
     дописавши
    0.69
     estekak
    0.69
    glEnd
    0.68
     endblock
    0.68
    Activations Density 1.687%

    No Known Activations