© 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. 1-RES-MATRYOSHKA-DC
    7. 578
    Prev
    Next
    INDEX
    Explanations

    references to mathematical concepts involving hyperplanes, projective varieties, and algebraic geometry

    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
    HB
    -0.65
     HB
    -0.65
    bib
    -0.63
    FB
    -0.60
     Geb
    -0.59
    mb
    -0.58
    WB
    -0.57
    fb
    -0.57
    hb
    -0.57
    ibel
    -0.57
    POSITIVE LOGITS
     sub
    4.72
    sub
    4.19
     Sub
    4.13
    Sub
    4.09
    SUB
    3.41
     SUB
    3.41
     getSub
    2.86
     subs
    2.72
    サブ
    2.72
    getSub
    2.70
    Activations Density 0.135%

    No Known Activations