© 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. 15797
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas

    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
     الحره
    -0.92
     mapStateToProps
    -0.82
     betweenstory
    -0.79
     surla
    -0.79
     InputDecoration
    -0.75
    UserScript
    -0.74
    出版年
    -0.71
    CloseOperation
    -0.70
    __':
    -0.69
    存于互联网档案馆
    -0.67
    POSITIVE LOGITS
    ่อ
    0.50
    gatsby
    0.47
    EndContext
    0.44
    ent
    0.44
    rientes
    0.43
    <u>
    0.43
     crossorigin
    0.42
     '.';
    0.42
    uire
    0.42
     bil
    0.42
    Activations Density 0.014%

    No Known Activations