© 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. 10031
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically commas and other similar characters

    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
     tornillo
    -0.49
     unnamed
    -0.48
    DISK
    -0.48
    !*\
    -0.45
    ViewById
    -0.44
    WithMany
    -0.44
    atist
    -0.44
    erek
    -0.44
    Tbh
    -0.43
     Band
    -0.43
    POSITIVE LOGITS
     referrerpolicy
    0.82
     nahilalakip
    0.72
    ########.
    0.69
    RuleContext
    0.68
    RegressionTest
    0.67
     صوتيه
    0.65
    XMLSchema
    0.59
    DeleteBehavior
    0.59
     للمعارف
    0.58
     Normdatei
    0.57
    Activations Density 0.015%

    No Known Activations