© 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. 11972
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notation related to summation and polynomials

    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
     kasarigan
    -0.64
    béco
    -0.60
    FormTagHelper
    -0.59
    endenza
    -0.59
    Geschiedenis
    -0.57
     glab
    -0.56
    Datuak
    -0.55
     perte
    -0.55
     présidentielle
    -0.54
     wicket
    -0.53
    POSITIVE LOGITS
    substack
    4.84
    hdashline
    0.66
     otomatig
    0.63
     مواليد
    0.57
    unic
    0.56
    Демографія
    0.56
    icolo
    0.56
    anek
    0.55
    HasColumnName
    0.55
    oine
    0.54
    Activations Density 0.000%

    No Known Activations