© 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. 6273
    Prev
    Next
    INDEX
    Explanations

    conjunctions and coordinating phrases that connect ideas or clauses

    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
    ніципа
    -0.64
    SourceChecksum
    -0.59
     viewType
    -0.57
     Italijanski
    -0.52
     surla
    -0.52
     hence
    -0.51
    hence
    -0.50
     heures
    -0.50
     dikem
    -0.49
     Dies
    -0.49
    POSITIVE LOGITS
     autorytatywna
    0.73
     Simplemente
    0.73
     simplesmente
    0.72
     simply
    0.69
     simplemente
    0.63
     StatefulWidget
    0.63
    جغرافيا
    0.59
     BrowserRouter
    0.59
    Simply
    0.59
     سكانية
    0.59
    Activations Density 0.246%

    No Known Activations