© 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. 0-RES-MATRYOSHKA-DC
    7. 12075
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terminology related to physics, electricity, and engineering

    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
    OrNil
    -0.83
    enumi
    -0.77
    ArrowToggle
    -0.73
     ویکی‌پدی
    -0.67
    StoryboardSegue
    -0.67
     disambiguazione
    -0.65
     esternos
    -0.63
    thâu
    -0.62
    \{\\
    -0.60
     autorytatywna
    -0.59
    POSITIVE LOGITS
     endif
    3.66
     endforeach
    1.88
     endfor
    1.69
    ENDIF
    1.42
     endwhile
    1.05
    endwhile
    0.77
    itet
    0.76
    Scenario
    0.68
    endforeach
    0.66
    ANTED
    0.63
    Activations Density 0.012%

    No Known Activations