© 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. 0-RES-MATRYOSHKA-DC
    7. 12005
    Prev
    Next
    INDEX
    Explanations

    sections related to figure legends or legends

    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
     legends
    -0.79
    MigrationBuilder
    -0.76
     legendary
    -0.68
     referenties
    -0.68
     myths
    -0.66
     myth
    -0.66
    Билгалдахарш
    -0.66
    ']").
    -0.65
     Мексичка
    -0.63
    UnsafeEnabled
    -0.63
    POSITIVE LOGITS
    legend
    1.84
    Legend
    1.52
     Legend
    0.88
    LEGEND
    0.66
    Comrade
    0.58
     raisonnable
    0.53
     conclusão
    0.53
    schild
    0.51
     compréhen
    0.50
     vastaan
    0.50
    Activations Density 0.000%

    No Known Activations