© 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. 5814
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Tonton" or similar, focusing on identifying references to "ton" as a name or term

    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
     createSlice
    -0.55
    ่านั้น
    -0.54
    ็จ
    -0.54
    NameInMap
    -0.54
     Donnelly
    -0.53
    ones
    -0.51
     bArr
    -0.51
     täh
    -0.50
     JADX
    -0.50
    cheibe
    -0.50
    POSITIVE LOGITS
    ton
    3.91
    TON
    3.34
     ton
    2.56
    tons
    2.34
    Ton
    2.34
     TON
    2.31
     Ton
    2.20
    tonne
    1.73
    тон
    1.63
    tona
    1.62
    Activations Density 0.019%

    No Known Activations