© 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. 20927
    Prev
    Next
    INDEX
    Explanations

    references to automated systems or processes

    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
     estimés
    -0.72
    y
    -0.62
    iness
    -0.61
    rostis
    -0.59
    PostConstruct
    -0.59
     inves
    -0.58
     iCloud
    -0.57
     Miro
    -0.57
     auto
    -0.57
     kitty
    -0.57
    POSITIVE LOGITS
    Automated
    0.85
     devenus
    0.85
     méri
    0.82
    Datuak
    0.80
    ("]");
    0.80
     automation
    0.80
     élect
    0.78
     contactez
    0.77
    Automation
    0.77
     automate
    0.77
    Activations Density 0.004%

    No Known Activations