© 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. 2260
    Prev
    Next
    INDEX
    Explanations

    image tags

    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
    cshtml
    -0.63
    évaluateur
    -0.60
    ős
    -0.57
     Obrador
    -0.56
     Emory
    -0.56
    adilan
    -0.55
    abrigo
    -0.54
    zzlement
    -0.54
    {@
    -0.54
    whenever
    -0.54
    POSITIVE LOGITS
    ![](
    3.66
    LikeLike
    0.85
    [](
    0.71
    LikeLiked
    0.68
    sizeCache
    0.65
    ligente
    0.64
     [](
    0.64
     ProtoMessage
    0.62
    `{.
    0.60
    abos
    0.59
    Activations Density 0.002%

    No Known Activations