© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15048
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation or specific punctuation patterns within the text

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .)
    -0.79
     --
    -0.63
    ↵↵
    -0.63
     b
    -0.62
    --
    -0.59
     relative
    -0.57
    </sub>
    -0.54
     "
    -0.54
    ).
    -0.54
     z
    -0.53
    POSITIVE LOGITS
     myſelf
    1.03
     Efq
    0.94
    FieldBuilder
    0.88
     himſelf
    0.86
    ChildScrollView
    0.86
    oredCriteria
    0.84
    Portale
    0.83
     itſelf
    0.83
     cdti
    0.79
    TypedDataSet
    0.78
    Activations Density 0.038%

    No Known Activations