© 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. 6130
    Prev
    Next
    INDEX
    Explanations

    references to chemical structures, specific molecules, or related terminology

    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
    duğu
    -0.67
    SourceChecksum
    -0.63
     CreateTagHelper
    -0.57
     Paglinawan
    -0.56
    Tracce
    -0.56
    awtextra
    -0.56
     phosphate
    -0.55
    astify
    -0.55
    createStatement
    -0.54
    تقاوى
    -0.54
    POSITIVE LOGITS
     äldre
    0.63
     épaules
    0.61
    featureID
    0.60
     äta
    0.60
     dianteiro
    0.56
     världen
    0.54
     proprietà
    0.53
     réguli
    0.51
     vux
    0.51
     المعيارى
    0.51
    Activations Density 2.112%

    No Known Activations