© 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. 2970
    Prev
    Next
    INDEX
    Explanations

    instances of the word "create" or its variants, indicating that it detects mentions of creating or making something

    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
     generation
    -1.55
     Generation
    -1.53
     generated
    -1.49
    Generation
    -1.49
     GENERATION
    -1.47
     Generated
    -1.45
    generation
    -1.41
    generated
    -1.30
     Generating
    -1.27
     GENER
    -1.23
    POSITIVE LOGITS
     creating
    0.98
     creates
    0.94
     create
    0.93
     Réponses
    0.90
    verwijspagina
    0.84
     créer
    0.83
     crear
    0.81
     crée
    0.80
     Creates
    0.77
     menciptakan
    0.77
    Activations Density 0.059%

    No Known Activations