© 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. 1-RES-MATRYOSHKA-DC
    7. 368
    Prev
    Next
    INDEX
    Explanations

    references to specific types of cells, especially "cell" and its variants

    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
    SourceChecksum
    -0.72
    elemField
    -0.68
    WireFormatLite
    -0.67
    AndEndTag
    -0.60
    TagMode
    -0.59
     faune
    -0.59
    InvalidProtocol
    -0.59
     vectorielles
    -0.58
    TintMode
    -0.57
    enyum
    -0.57
    POSITIVE LOGITS
     cell
    4.53
     Cell
    4.16
    cell
    4.09
    Cell
    3.92
     CELL
    3.77
     cells
    3.72
    CELL
    3.53
     Cells
    3.48
    cells
    3.39
     CELLS
    3.22
    Activations Density 0.951%

    No Known Activations