© 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. 11097
    Prev
    Next
    INDEX
    Explanations

    representations of mathematical expressions and notation

    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
    ticale
    -0.56
     BnF
    -0.54
    glBegin
    -0.52
     endwhile
    -0.52
    PhysRev
    -0.48
    ="#"
    -0.48
    bulos
    -0.47
     Deel
    -0.47
    lia
    -0.47
     sứ
    -0.47
    POSITIVE LOGITS
    mathit
    2.86
    KommentareTeilen
    0.69
     trajets
    0.68
    tagHelperRunner
    0.68
     disambiguazione
    0.65
     Reverso
    0.59
    Hentet
    0.59
    NUMX
    0.58
    OGND
    0.57
    Listo
    0.56
    Activations Density 0.002%

    No Known Activations