© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 2716
    Prev
    Next
    INDEX
    Explanations

    references to a mathematical package used for writing equations

    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
    amssymb
    -2.58
    __(/*!
    -0.90
    AndEndTag
    -0.85
    TestingModule
    -0.76
    DockStyle
    -0.76
    abestanden
    -0.71
     CreateTagHelper
    -0.69
     Wicidata
    -0.66
    Portail
    -0.65
    RectangleBorder
    -0.65
    POSITIVE LOGITS
    amsmath
    4.09
    Mediabestanden
    0.52
     eins
    0.49
     Spann
    0.48
    avanaugh
    0.47
     naso
    0.47
    PyExc
    0.47
    getActiveSheet
    0.46
     mxArray
    0.46
     TextAlign
    0.45
    Activations Density 0.001%

    No Known Activations