© 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. 1-RES-MATRYOSHKA-DC
    7. 995
    Prev
    Next
    INDEX
    Explanations

    references to the calculation or evaluation of a mathematical product

    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
    arXiv
    -0.69
     "..\..\
    -0.66
     Materials
    -0.64
    materials
    -0.63
    Vorlage
    -0.61
     "..\..\..\
    -0.60
    SourceChecksum
    -0.60
     Papel
    -0.60
     Материал
    -0.59
    ValueStyle
    -0.59
    POSITIVE LOGITS
     product
    4.38
    product
    3.89
     Product
    3.84
    Product
    3.70
     products
    3.55
     PRODUCT
    3.34
     Products
    3.22
    PRODUCT
    3.11
    products
    3.09
     producto
    3.09
    Activations Density 0.198%

    No Known Activations