© 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. 5974
    Prev
    Next
    INDEX
    Explanations

    the action of creating or instantiating objects or components

    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
     generated
    -1.31
     Generated
    -1.31
     generation
    -1.20
    Generated
    -1.10
     Generation
    -1.07
    Generation
    -1.02
     GENERATION
    -1.00
     GENERATED
    -1.00
    generated
    -0.98
    generation
    -0.98
    POSITIVE LOGITS
    create
    1.95
    Create
    1.51
    CREATE
    1.34
     Create
    1.30
     create
    1.20
     CREATE
    1.13
     создать
    0.81
     Crear
    0.80
    创建一个
    0.79
    criar
    0.76
    Activations Density 0.034%

    No Known Activations