© 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. 11247
    Prev
    Next
    INDEX
    Explanations

    reports of gene expression levels in tissue samples

    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
     tissue
    -0.60
     Tissue
    -0.58
     tore
    -0.52
    alapa
    -0.48
     steigen
    -0.48
    ilija
    -0.47
    anto
    -0.47
    Tissue
    -0.47
    мас
    -0.47
     transparent
    -0.46
    POSITIVE LOGITS
     tissues
    1.88
     Tissues
    1.41
     Jefus
    0.80
     ſeveral
    0.77
     Majefty
    0.77
     reaſon
    0.76
     Reſ
    0.76
     Anſ
    0.76
     Chriftian
    0.76
     Monfieur
    0.75
    Activations Density 0.003%

    No Known Activations