© 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. 14924
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and dialogue indicators in conversational or narrative text

    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
     تضيفلها
    -0.69
    GEBURTSDATUM
    -0.67
     userManager
    -0.60
    اریخ
    -0.57
    Viited
    -0.54
    Charsets
    -0.54
    StateManager
    -0.54
    Przypisy
    -0.53
     án
    -0.51
    seamnă
    -0.51
    POSITIVE LOGITS
    inkin
    0.56
    ->__
    0.50
    MockBean
    0.46
    "]}
    0.46
    *>(
    0.45
    foundland
    0.45
     gere
    0.45
    ASIN
    0.44
     Etude
    0.44
    ")));
    0.44
    Activations Density 0.020%

    No Known Activations