© 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. 24982
    Prev
    Next
    INDEX
    Explanations

    references to specific drugs and their effects in scientific contexts

    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
    numerusform
    -0.74
    expandindo
    -0.70
    WriteBarrier
    -0.67
    mybatisplus
    -0.66
    RectangleBorder
    -0.64
    ########.
    -0.62
    WithMany
    -0.61
    withOpacity
    -0.60
      (
    -0.58
     ModelRenderer
    -0.57
    POSITIVE LOGITS
     gyhoeddwyd
    0.61
    Timing
    0.53
     Timing
    0.52
     Nicaragua
    0.50
    Erreferentziak
    0.48
     timing
    0.47
     porta
    0.47
     arter
    0.46
    homonymie
    0.46
    ratto
    0.46
    Activations Density 0.020%

    No Known Activations