© 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. 6694
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific LaTeX command sequences related to the "textrm" environment

    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
     L
    -0.65
     E
    -0.60
    Heim
    -0.55
     
    -0.53
     “
    -0.52
     D
    -0.52
    .
    -0.52
     ge
    -0.52
    !
    -0.51
    ckt
    -0.50
    POSITIVE LOGITS
    textrm
    3.42
    出版年
    1.06
     Majefty
    1.00
     pleaſure
    0.94
     iſt
    0.92
    textnormal
    0.92
     Jefus
    0.91
     raiſ
    0.90
     Reſ
    0.90
     Chriſt
    0.88
    Activations Density 0.005%

    No Known Activations