© 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. 7379
    Prev
    Next
    INDEX
    Explanations

    references to cytological or cellular features in scientific or medical texts

    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
    อาด
    -0.59
     StatefulWidget
    -0.56
     Ham
    -0.52
    BuildContext
    -0.51
     cell
    -0.49
    ModelSerializer
    -0.49
    writeHead
    -0.49
    gw
    -0.49
    Cell
    -0.49
    PrototypeOf
    -0.48
    POSITIVE LOGITS
     cyto
    3.42
     Cyto
    2.59
    Cyto
    2.41
    cyto
    2.31
     cytometry
    1.20
     Cytometry
    1.10
     cytoplasmic
    1.05
     cytotoxic
    1.04
     cytochrome
    0.96
     cytotoxicity
    0.93
    Activations Density 0.004%

    No Known Activations