© 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. 4130
    Prev
    Next
    INDEX
    Explanations

    references to mathematical expressions that specify how certain parameters are provided or defined

    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
     ChromeDriver
    -0.85
     Roskov
    -0.71
    webElementXpaths
    -0.66
    CopyWith
    -0.65
     ExecuteAsync
    -0.65
     Apes
    -0.63
    VIAF
    -0.61
    юрпри
    -0.60
    ColumnHeaders
    -0.60
     ligiloj
    -0.58
    POSITIVE LOGITS
    +:+
    0.70
    lastonbury
    0.60
    efois
    0.56
    ISF
    0.55
     telinga
    0.54
    aime
    0.54
    ValueGenerated
    0.53
     lèvres
    0.52
     representado
    0.52
     origines
    0.52
    Activations Density 0.065%

    No Known Activations