© 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. 22381
    Prev
    Next
    INDEX
    Explanations

    references to judicial nominees and related political 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
    Negative Logits
    導
    -0.46
     
    -0.43
     I
    -0.43
    导
    -0.41
    ```
    -0.40
     fas
    -0.40
     Sarko
    -0.39
    IP
    -0.39
    uction
    -0.39
    執
    -0.39
    POSITIVE LOGITS
    Geplaatst
    1.08
    SharedCtor
    0.93
    GEBURTSDATUM
    0.92
     nominee
    0.91
    parsedMessage
    0.90
    queryInterface
    0.88
     nominees
    0.86
     autorytatywna
    0.85
     AspNetCore
    0.85
    ThroughAttribute
    0.85
    Activations Density 0.046%

    No Known Activations