© 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. 7191
    Prev
    Next
    INDEX
    Explanations

    references to quantities involving large numbers or measurements

    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
     AssemblyVersion
    -0.93
    URLException
    -0.91
    featureID
    -0.90
    parsedMessage
    -0.88
    AddTagHelper
    -0.88
    :✨
    -0.85
    !*\
    -0.84
    цездатний
    -0.84
    djangoproject
    -0.81
    GenerationType
    -0.81
    POSITIVE LOGITS
     hundred
    2.83
    hundred
    2.41
     Hundred
    2.33
    Hundred
    2.06
     thousand
    1.92
     HUND
    1.83
    thousand
    1.58
     hundert
    1.52
     fifty
    1.37
     Thousand
    1.37
    Activations Density 0.023%

    No Known Activations