© 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. 20717
    Prev
    Next
    INDEX
    Explanations

    references to companies or organizational entities

    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
    Not in Any Lists

    No Comments

    Negative Logits
     business
    -0.65
     “
    -0.60
    \",\"
    -0.59
     Business
    -0.59
    =”
    -0.59
     (“
    -0.58
    ítás
    -0.57
     Zacks
    -0.56
    istos
    -0.55
     Tổng
    -0.55
    POSITIVE LOGITS
     Companies
    1.22
     COMPANY
    1.16
    companies
    1.11
    Companies
    1.10
    COMPANY
    1.10
     COMPANIES
    1.08
     المعيارى
    1.04
     Company
    1.03
     companies
    1.02
    AccessorTable
    1.02
    Activations Density 0.024%

    No Known Activations