© 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. 7123
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical or measurement data

    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
     $('#
    -0.59
    textLabel
    -0.57
    .^
    -0.55
    жер
    -0.55
     Fik
    -0.55
    migrationBuilder
    -0.54
    $-
    -0.53
    ^-
    -0.53
     *
    -0.52
    ه
    -0.52
    POSITIVE LOGITS
    ·
    2.02
     ·
    1.36
    ··
    1.02
     ··
    1.02
    ∙
    0.96
     ∙
    0.90
    ·
    0.90
    ···
    0.87
    ㆍ
    0.87
    ······
    0.87
    Activations Density 0.011%

    No Known Activations