© 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. 25853
    Prev
    Next
    INDEX
    Explanations

    text related to reviewer feedback and suggestions

    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
     BrowserModule
    -0.69
    expandindo
    -0.53
    matchCondition
    -0.52
    atimes
    -0.52
    :+:
    -0.52
    وعة
    -0.51
    ArgsConstructor
    -0.50
     />);
    -0.48
    licht
    -0.48
     tartalomajánló
    -0.48
    POSITIVE LOGITS
     distanciation
    0.74
    WithIOException
    0.72
     ویکی‌پدیای
    0.68
    PMailer
    0.64
     reviewers
    0.62
     Cientí
    0.59
     twain
    0.59
    PageContext
    0.57
    ívne
    0.56
    veston
    0.55
    Activations Density 0.018%

    No Known Activations