© 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. 12-RES-MATRYOSHKA-DC
    7. 32347
    Prev
    Next
    INDEX
    Explanations

    terms related to cytotoxicity and cellular responses to substances

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    writeHead
    -0.68
     Beek
    -0.63
    an
    -0.59
     ways
    -0.58
    drawString
    -0.58
    </b>
    -0.56
    CHO
    -0.56
    lix
    -0.56
    </i>
    -0.55
     Kall
    -0.54
    POSITIVE LOGITS
     cyto
    1.66
     Cyto
    1.57
    Cyto
    1.39
    cyto
    1.38
     myſelf
    1.16
    IsContent
    1.10
     cytochrome
    1.09
     uſed
    1.08
     houſe
    1.06
     itſelf
    1.06
    Activations Density 0.006%

    No Known Activations