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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15478
    Prev
    Next
    INDEX
    Explanations

    tokens related to Chinese morphological suffixes, prefixes, or linguistic markers

    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
     OMITBAD
    -1.04
     prêtres
    -0.88
    ，
    -0.87
     prisonniers
    -0.81
     démocr
    -0.80
    、
    -0.78
    Kontrola
    -0.78
    useNewUrlParser
    -0.78
    ьаж
    -0.76
    他
    -0.74
    POSITIVE LOGITS
    なのでしょう
    0.63
    jspx
    0.53
    もありますが
    0.51
     and
    0.49
     out
    0.49
    featureID
    0.47
    图源
    0.47
     for
    0.46
    mo
    0.46
    ri
    0.45
    Activations Density 0.007%

    No Known Activations