© 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. 1-RES-MATRYOSHKA-DC
    7. 290
    Prev
    Next
    INDEX
    Explanations

    references to mathematical or scientific functions or functions related to complex models

    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
     ingrat
    -0.58
    География
    -0.58
     margins
    -0.54
     Wikispecies
    -0.53
    بوابة
    -0.53
     cenário
    -0.52
     unknownFields
    -0.52
    Портал
    -0.51
    تقاوى
    -0.51
     Locality
    -0.51
    POSITIVE LOGITS
     function
    4.59
     Function
    4.09
    function
    4.06
     functions
    3.81
    Function
    3.66
     FUNCTION
    3.59
     Functions
    3.56
    functions
    3.33
    FUNCTION
    3.19
     fonction
    3.16
    Activations Density 0.248%

    No Known Activations