© 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. 7212
    Prev
    Next
    INDEX
    Explanations

    mentions of specific technical terms related to measurements, parameters, and mathematical notation

    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
     виправивши
    -0.79
    migrationBuilder
    -0.75
     <>",
    -0.73
    httphttps
    -0.69
     ivelany
    -0.68
    OGND
    -0.66
    LookAnd
    -0.66
    <bos>
    -0.65
    esModule
    -0.65
     ModelExpression
    -0.64
    POSITIVE LOGITS
    ↵↵
    0.56
    <eos>
    0.47
    ness
    0.47
    iální
    0.47
     Kiev
    0.47
    Honduras
    0.45
     barvy
    0.44
     modelleri
    0.44
    Amerika
    0.43
    [].
    0.43
    Activations Density 4.336%

    No Known Activations