© 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. 22-RES-MATRYOSHKA-DC
    7. 34
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to biological and chemical processes, especially within the realm of cell biology and immunology.

    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
     spirito
    -0.63
    Ety
    -0.60
    NIST
    -0.59
    uteen
    -0.59
     meille
    -0.57
    RMSE
    -0.56
    Teknik
    -0.55
    FFT
    -0.55
     IllegalArgument
    -0.54
    KOH
    -0.54
    POSITIVE LOGITS
     expression
    0.92
     signaling
    0.91
     cellular
    0.90
     intracellular
    0.88
     protein
    0.87
     gene
    0.85
     genes
    0.84
     regulation
    0.83
     functionally
    0.83
     proteins
    0.82
    Activations Density 8.491%

    No Known Activations