© 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. 3649
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving special functions, notation, and symbols commonly used in advanced mathematical or scientific texts

    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
     doInBackground
    -0.80
    InputTagHelper
    -0.71
    uitton
    -0.63
    useEffect
    -0.63
     snippetHide
    -0.63
    tvguidetime
    -0.62
     ziua
    -0.61
    ForValue
    -0.61
     препратки
    -0.61
    djangoproject
    -0.60
    POSITIVE LOGITS
    ast
    3.25
    AST
    2.06
     ast
    1.98
    Ast
    1.83
     Ast
    1.77
    asts
    1.66
     AST
    1.66
    asto
    1.34
    asting
    1.28
    asta
    1.25
    Activations Density 0.037%

    No Known Activations