© 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. 22425
    Prev
    Next
    INDEX
    Explanations

    details related to statistical updates and accuracy in data reporting

    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
    UrlResolution
    -0.70
     سكانية
    -0.67
    ]--;
    -0.66
    ardized
    -0.65
    $_['
    -0.63
    laquo
    -0.62
     Italijani
    -0.61
     Followed
    -0.60
    yntaxException
    -0.59
     suivie
    -0.59
    POSITIVE LOGITS
    FlatList
    0.56
    rrggbb
    0.47
    最新
    0.45
    Atual
    0.44
    ধ
    0.44
     currently
    0.42
    IntoConstraints
    0.42
     surla
    0.42
     onData
    0.42
    現状
    0.42
    Activations Density 0.111%

    No Known Activations