© 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. 21063
    Prev
    Next
    INDEX
    Explanations

    biochemical terms related to molecular interactions and specific assay results

    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
     Jinping
    -0.48
    Wz
    -0.45
     CEOs
    -0.44
    מוס
    -0.44
     stripper
    -0.44
    TagNumber
    -0.44
     dongle
    -0.44
     Isra
    -0.43
     Sado
    -0.43
    ophenyl
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    0.78
    __*/
    0.69
    principalTable
    0.68
    oredCriteria
    0.67
    MemoryWarning
    0.66
     propOrder
    0.64
    новниш
    0.62
    fjspx
    0.62
    verwijspagina
    0.61
     تضيفلها
    0.60
    Activations Density 0.316%

    No Known Activations