© 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. 24561
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage within 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
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.69
    Jeografia
    -0.67
    ParallelGroup
    -0.58
    落とし
    -0.54
    PrototypeOf
    -0.53
     LoggerFactory
    -0.52
    mybatisplus
    -0.50
    ORAGE
    -0.49
    Atsauces
    -0.49
    ftagPool
    -0.47
    POSITIVE LOGITS
    存于互联网档案馆
    0.73
    
    0.63
    czegó
    0.59
    roek
    0.59
    osexuality
    0.59
    ImageContext
    0.58
     iſt
    0.57
     ſtate
    0.57
    ngoing
    0.56
    curious
    0.56
    Activations Density 0.018%

    No Known Activations