© 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. 7277
    Prev
    Next
    INDEX
    Explanations

    references to supplementary materials and supporting information

    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
    lementary
    -0.95
    Supplementary
    -0.83
     Supplementary
    -0.66
     respald
    -0.60
     complementar
    -0.56
     complément
    -0.56
     adicionales
    -0.55
     complementary
    -0.55
     hjelp
    -0.52
     supplementary
    -0.52
    POSITIVE LOGITS
    supp
    2.31
     supp
    1.75
     Supp
    1.70
    Supp
    1.65
     suppression
    1.23
     Suppression
    1.18
     suppress
    1.14
     suppressed
    1.14
     suppressor
    1.12
    SUP
    1.05
    Activations Density 0.010%

    No Known Activations