© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 2744
    Prev
    Next
    INDEX
    Explanations

    references to motion vectors and techniques for motion detection and compensation

    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
    RenderAtEndOf
    -0.56
     godfather
    -0.52
     cómod
    -0.52
     DataLoader
    -0.52
    //
    -0.50
    bayes
    -0.48
     rout
    -0.47
    GBT
    -0.46
     Comfor
    -0.46
     cómodo
    -0.46
    POSITIVE LOGITS
     متعلقه
    0.82
    +#+#
    0.81
     Вікі
    0.66
     estimés
    0.63
    complexType
    0.61
    MigrationBuilder
    0.61
     مشين
    0.60
    SizeF
    0.59
     كورة
    0.58
     doch
    0.57
    Activations Density 0.949%

    No Known Activations