© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15100
    Prev
    Next
    INDEX
    Explanations

    the presence of numerical data, such as section numbers, percentages, 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
     surla
    -0.96
     pinulongan
    -0.93
    MigrationBuilder
    -0.84
    expandindo
    -0.83
     nahilalakip
    -0.82
    AnchorStyles
    -0.81
    webElementGuid
    -0.77
     /*#__
    -0.77
    localctx
    -0.73
    \}.
    -0.72
    POSITIVE LOGITS
     purpoſe
    0.77
    <bos>
    0.68
     raiſ
    0.63
     chofe
    0.63
     ſtate
    0.56
     pleaſure
    0.56
     houſe
    0.56
     the
    0.56
     hozz
    0.55
    Partager
    0.55
    Activations Density 3.045%

    No Known Activations