© 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. 18716
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods

    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
    toHaveBeenCalled
    -0.57
    myModal
    -0.57
    ,
    -0.55
    AnchorStyles
    -0.54
    .
    -0.50
    hind
    -0.46
     violenza
    -0.45
     SQLException
    -0.45
    adaptiveStyles
    -0.45
    LError
    -0.43
    POSITIVE LOGITS
    verwijspagina
    0.85
     betweenstory
    0.82
    :✨
    0.75
    AntiForgeryToken
    0.73
    دانشنامهٔ
    0.72
    UnknownFields
    0.71
     '\\;'
    0.71
    SourceChecksum
    0.68
     Ema
    0.68
     Baillargeon
    0.68
    Activations Density 0.031%

    No Known Activations