© 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. 12086
    Prev
    Next
    INDEX
    Explanations

    references to specific chemical compounds involved in material processing and structural analysis

    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
    énario
    -0.68
     مشين
    -0.60
    EndContext
    -0.57
     FetchType
    -0.57
    RenderAtEndOf
    -0.57
    白石
    -0.56
    ɵɵelementEnd
    -0.55
    ))/(
    -0.55
    ArgsConstructor
    -0.54
     ErrIntOverflow
    -0.54
    POSITIVE LOGITS
    calar
    1.19
     sinter
    0.81
     Dickens
    0.75
    Thy
    0.69
    COUVER
    0.66
     sickness
    0.66
     footing
    0.65
     moor
    0.65
     Sinter
    0.64
     Boyd
    0.62
    Activations Density 0.072%

    No Known Activations