© 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. 26000
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and commas in lists or series of items

    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
    IntoConstraints
    -0.78
    yntaxException
    -0.69
     poveznice
    -0.65
    __':
    -0.63
    __":
    -0.60
     Inquisition
    -0.60
     Shakspeare
    -0.58
     Gött
    -0.57
    Personensuche
    -0.57
    TargetException
    -0.57
    POSITIVE LOGITS
    énario
    0.67
     ${({
    0.65
     estekak
    0.62
    DOCTYPE
    0.61
     المعيارى
    0.61
     Wer
    0.60
    
    0.60
    γωγ
    0.57
     }^{(
    0.55
    AnchorStyles
    0.54
    Activations Density 0.008%

    No Known Activations