© 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. 4219
    Prev
    Next
    INDEX
    Explanations

    numerical data, formulas, or mathematical expressions

    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
    fromnode
    -0.64
    Sitemap
    -0.64
    Trama
    -0.63
    styleType
    -0.60
    createStatement
    -0.60
     amables
    -0.59
    dafx
    -0.59
    ánicos
    -0.59
     Meteor
    -0.57
    Архівовано
    -0.57
    POSITIVE LOGITS
    Brainz
    0.57
     eventdata
    0.57
     quadruple
    0.56
     Roskov
    0.55
     виправивши
    0.55
    basicConfig
    0.54
     Arqu
    0.54
     Canarias
    0.54
    cion
    0.54
     Cabral
    0.53
    Activations Density 0.267%

    No Known Activations