© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 395
    Prev
    Next
    INDEX
    Explanations

    references to specific punctuation marks, primarily periods and dots

    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
     itſelf
    -1.75
     myſelf
    -1.70
     Theſe
    -1.67
     Reſ
    -1.63
    \
    -1.62
     Efq
    -1.59
     pleaſure
    -1.55
     themſelves
    -1.54
     Monfieur
    -1.54
     Houſe
    -1.53
    POSITIVE LOGITS
     \
    1.84
     .
    1.13
     /
    1.04
     ...
    0.97
     $\
    0.95
     '
    0.94
     ​
    0.94
     @
    0.88
     $
    0.87
     -
    0.86
    Activations Density 0.806%

    No Known Activations