© 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. 13917
    Prev
    Next
    INDEX
    Explanations

    references to the word "de" which is often used as "of" in French

    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
    fxml
    -0.76
    queryInterface
    -0.65
    peutic
    -0.60
    Bakgrunnsstoff
    -0.60
    ignac
    -0.59
    ็จ
    -0.57
    scape
    -0.56
     Jep
    -0.54
    henswürdigkeiten
    -0.53
    CPtr
    -0.53
    POSITIVE LOGITS
     ainfi
    0.66
     dianteiro
    0.63
     initComponents
    0.62
    Искәрмәләр
    0.60
     født
    0.59
     Dicapai
    0.58
     ulteriori
    0.57
    loč
    0.56
     hvil
    0.54
    ikala
    0.54
    Activations Density 0.007%

    No Known Activations