© 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. 3-RES-MATRYOSHKA-DC
    7. 1660
    Prev
    Next
    INDEX
    Explanations

    words or phrases that describe processes or actions being implemented

    oai_token-act-pair · gemini-2.0-flash
    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
    UnusedPrivate
    -0.75
    tonsoft
    -0.60
     سكانية
    -0.60
    !*\
    -0.59
    //
    -0.58
    parsedMessage
    -0.57
    ()['
    -0.54
     BFS
    -0.54
    HtmlAttribute
    -0.51
     Monfieur
    -0.51
    POSITIVE LOGITS
     HttpNotFound
    0.68
    賀状
    0.64
    ]-->
    0.55
    PositiveButton
    0.54
    MLLoader
    0.51
     itinéraires
    0.51
     surla
    0.50
    Nationalité
    0.49
    umpulkan
    0.48
     везе
    0.48
    Activations Density 3.175%

    No Known Activations