© 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. 3191
    Prev
    Next
    INDEX
    Explanations

    references to a programming language or framework, specifically "cy" related terms

    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
     cycle
    -1.23
     cycles
    -1.20
    Cycle
    -1.16
     Cycle
    -1.13
     CYCLE
    -1.12
    cycle
    -1.10
    XmlAccessorType
    -1.05
     ciclo
    -1.03
     Cycles
    -1.02
     ciclos
    -0.99
    POSITIVE LOGITS
    cy
    3.11
     cy
    2.22
     Cy
    2.19
    Cy
    2.02
    CY
    1.66
     CY
    1.33
    cies
    1.12
     cytos
    1.00
    cys
    0.87
    cym
    0.83
    Activations Density 0.029%

    No Known Activations