© 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. 30833
    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
     connaissent
    -0.44
     wrze
    -0.39
    <bos>
    -0.39
     bodas
    -0.39
    ,
    -0.37
     gants
    -0.37
    ↵↵
    -0.36
    then
    -0.36
     otten
    -0.36
     procès
    -0.36
    POSITIVE LOGITS
     noqa
    0.93
    mybatisplus
    0.91
    RectangleBorder
    0.83
    ArrowToggle
    0.82
    kloped
    0.81
    moiselle
    0.79
    醐
    0.79
     AttributeSet
    0.78
     AssemblyVersion
    0.77
    @[+][
    0.75
    Activations Density 0.000%

    No Known Activations