© 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. 15429
    Prev
    Next
    INDEX
    Explanations

    references to specific phrases indicating emphasis or importance

    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
     بيها
    -0.70
     которые
    -0.58
     whose
    -0.54
    mtrl
    -0.54
    pectiva
    -0.54
     which
    -0.52
    ρέ
    -0.52
     CURLOPT
    -0.52
     MongoClient
    -0.52
     waaronder
    -0.52
    POSITIVE LOGITS
    Autoritní
    0.81
    Portale
    0.72
    mapStateToProps
    0.64
    udadera
    0.62
    __*/
    0.61
     
    0.60
     TestBed
    0.58
    Démographie
    0.57
     Italijanski
    0.57
    Искәрмәләр
    0.56
    Activations Density 0.288%

    No Known Activations