© 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. 3855
    Prev
    Next
    INDEX
    Explanations

    references to missing data and data imputation studies

    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
     lack
    -0.93
     Lack
    -0.88
     mis
    -0.86
    Lack
    -0.86
    lack
    -0.77
    mis
    -0.77
    Mis
    -0.74
    ArrowToggle
    -0.74
     Mis
    -0.71
    MigrationBuilder
    -0.67
    POSITIVE LOGITS
     missing
    2.83
     Missing
    2.67
    Missing
    2.56
    missing
    2.56
     MISSING
    2.38
    MISSING
    1.83
     manquante
    1.08
     missed
    1.02
     misses
    1.00
    失踪
    0.96
    Activations Density 0.016%

    No Known Activations