© 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. 11078
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas, especially those involving special functions, fractions, roots, and constants

    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
    overset
    -1.47
    stackrel
    -1.07
     Arxivat
    -0.67
    underset
    -0.60
    ederos
    -0.59
     estekak
    -0.58
    RegressionTest
    -0.57
    Enllaços
    -0.57
    Välislingid
    -0.57
     prega
    -0.56
    POSITIVE LOGITS
    mathop
    2.59
    enumi
    0.56
    izung
    0.54
    otide
    0.54
    vosti
    0.54
    mtliche
    0.50
    blox
    0.50
    timg
    0.50
    DeleteMapping
    0.50
     onlyOwner
    0.49
    Activations Density 0.001%

    No Known Activations