© 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. 2893
    Prev
    Next
    INDEX
    Explanations

    complex mathematical products involving matrix operations and tensor contractions

    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
     sum
    -0.61
    sum
    -0.61
    Sum
    -0.60
     SUM
    -0.60
    SUM
    -0.55
     Sum
    -0.51
     atom
    -0.48
    ukai
    -0.48
     Sag
    -0.46
     somma
    -0.45
    POSITIVE LOGITS
    prod
    2.73
    ∏
    1.91
     prod
    1.78
    Prod
    1.63
     Prod
    1.38
    PROD
    1.19
     getProduct
    0.94
    product
    0.91
    Products
    0.89
    PRODUCT
    0.89
    Activations Density 0.004%

    No Known Activations