© 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. 28717
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly parentheses

    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
    Javadoc
    -0.56
     utafitiHapana
    -0.50
     Trá
    -0.50
     drunken
    -0.47
     Callahan
    -0.46
     nemlig
    -0.46
     OkHttpClient
    -0.45
    Vere
    -0.45
    AnimationsModule
    -0.44
     TextInput
    -0.44
    POSITIVE LOGITS
     Wikimedijinoj
    0.84
     Normdatei
    0.72
     AssemblyCulture
    0.68
     stanovnika
    0.63
    ArgumentParser
    0.61
     Spisak
    0.60
     surla
    0.59
    bootstrapcdn
    0.58
    Бахар
    0.57
    ंदीखरीदारी
    0.56
    Activations Density 0.045%

    No Known Activations