© 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. 2-RES-MATRYOSHKA-DC
    7. 3164
    Prev
    Next
    INDEX
    Explanations

    references to specific character types

    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
     char
    -1.02
     Char
    -1.01
    char
    -0.97
    Char
    -0.97
     letter
    -0.94
     Letter
    -0.92
    letter
    -0.90
    LETTER
    -0.88
     LETTER
    -0.87
     CHAR
    -0.87
    POSITIVE LOGITS
     character
    2.19
     characters
    1.89
     Character
    1.84
    character
    1.79
     Characters
    1.72
    Character
    1.67
    characters
    1.63
     CHARACTER
    1.61
    Characters
    1.41
     CHARACTERS
    1.40
    Activations Density 0.042%

    No Known Activations