© 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. 12837
    Prev
    Next
    INDEX
    Explanations

    references to specific instances of the word "character."

    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
    -0.56
     were
    -0.51
     original
    -0.46
    udd
    -0.46
     dinam
    -0.45
     Blush
    -0.45
    UMEN
    -0.45
    ندی
    -0.44
     Kreise
    -0.44
     U
    -0.44
    POSITIVE LOGITS
    Character
    1.09
     wireType
    0.94
    CHARACTER
    0.90
    ніципа
    0.83
    +#+
    0.82
    +#+#
    0.79
     Vikipedi
    0.77
    #+#
    0.75
     Normdatei
    0.75
    URLException
    0.75
    Activations Density 0.004%

    No Known Activations