© 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. 1-RES-MATRYOSHKA-DC
    7. 1099
    Prev
    Next
    INDEX
    Explanations

    references to the operation or functioning of uninterruptible power supply (UPS) systems

    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
     Carrillo
    -0.56
    icestershire
    -0.53
    ícios
    -0.52
     stimulants
    -0.51
     Hügel
    -0.50
    doria
    -0.50
    <!--
    -0.49
     rhestr
    -0.49
     Lübeck
    -0.49
     Vara
    -0.49
    POSITIVE LOGITS
     operation
    4.41
     Operation
    4.00
    operation
    3.86
     OPERATION
    3.80
    Operation
    3.73
     operations
    3.72
     Operations
    3.45
     operate
    3.36
    operations
    3.34
     oper
    3.25
    Activations Density 1.793%

    No Known Activations