© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7311
    Prev
    Next
    INDEX
    Explanations

    references to code preprocessing, including code that identifies specific instructions, macros, or structural elements within code

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    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
     disambiguazione
    -0.64
    aspectj
    -0.63
    queryInterface
    -0.60
    empêcher
    -0.59
    LayoutPanel
    -0.55
    /*
    -0.55
     JAXB
    -0.55
    JAXB
    -0.55
    slidesToShow
    -0.54
    Impact
    -0.54
    POSITIVE LOGITS
    endif
    4.50
     endif
    2.41
    endregion
    1.29
    ENDIF
    1.19
    endwhile
    0.97
    endfor
    0.95
    endforeach
    0.94
    ɵɵelementEnd
    0.85
     endregion
    0.79
    tagext
    0.76
    Activations Density 0.004%

    No Known Activations