© 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. 88
    Prev
    Next
    INDEX
    Explanations

    patterns related to specific algebraic and diagrammatic notation used in mathematical physics and category theory

    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
     ſeveral
    -1.16
     iſt
    -1.14
     themſelves
    -1.14
     ſever
    -1.13
     Theſe
    -1.13
     ſhall
    -1.11
     Anſ
    -1.10
     ſame
    -1.09
     myſelf
    -1.09
     Beſ
    -1.06
    POSITIVE LOGITS
     b
    1.59
     d
    1.47
     B
    1.47
     C
    1.43
     M
    1.41
     c
    1.41
     S
    1.41
     g
    1.41
     p
    1.38
     h
    1.38
    Activations Density 12.971%

    No Known Activations