© 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. 3548
    Prev
    Next
    INDEX
    Explanations

    patterns related to Unicode characters with diacritics, specifically accented letters

    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
     виправивши
    -0.97
     économies
    -0.80
     venons
    -0.79
    脚注の使い方
    -0.78
    ︎
    -0.78
     réfrig
    -0.75
    IndentedString
    -0.74
    UnsafeEnabled
    -0.74
    ítmény
    -0.74
     ainfi
    -0.73
    POSITIVE LOGITS
    é
    2.58
    É
    1.62
    eacute
    1.19
     é
    1.18
    és
    1.08
     É
    1.07
    éd
    0.96
    dé
    0.90
    éf
    0.88
    á
    0.88
    Activations Density 0.009%

    No Known Activations