© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 324
    Prev
    Next
    INDEX
    Explanations

    words related to cell biology, especially in the context of human cells and cultures.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Réalisation
    -0.50
    werken
    -0.50
    Guil
    -0.50
    CppCodeGen
    -0.49
    cisa
    -0.48
     Vieux
    -0.48
    wirk
    -0.47
    FileInput
    -0.47
     landmarks
    -0.47
    مح
    -0.46
    POSITIVE LOGITS
     cells
    1.35
     cell
    1.18
     cellules
    1.10
    cells
    1.09
     Cells
    1.06
     CELLS
    0.99
     células
    0.98
    cell
    0.97
    Cells
    0.96
     CELL
    0.88
    Activations Density 1.890%

    No Known Activations