© 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. 0-RES-MATRYOSHKA-DC
    7. 10982
    Prev
    Next
    INDEX
    Explanations

    lines describing polynomial or fractional spline correspondences

    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
     coincides
    -1.16
     coincided
    -1.00
     coincide
    -0.89
     corresponds
    -0.86
     émissions
    -0.66
     Chwiliwch
    -0.66
     privées
    -0.65
    IsContent
    -0.62
     épis
    -0.62
     doigts
    -0.62
    POSITIVE LOGITS
     correspond
    1.41
    ftal
    0.63
    higan
    0.59
    riculares
    0.56
     Norwood
    0.56
    λέον
    0.55
    sld
    0.55
     بتاريخ
    0.55
    cerne
    0.54
    ConverterFactory
    0.54
    Activations Density 0.002%

    No Known Activations