© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13764
    Prev
    Next
    INDEX
    Explanations

    the operation to activate or control a device

    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
     operativo
    -0.71
     operacional
    -0.59
     distract
    -0.59
     fédéral
    -0.59
     workman
    -0.57
     kual
    -0.57
     opération
    -0.56
     pleaſure
    -0.55
    AndEndTag
    -0.54
     tempio
    -0.54
    POSITIVE LOGITS
     operate
    1.66
     operates
    1.59
     Operate
    1.18
    operate
    1.07
    Operate
    0.85
     runs
    0.82
     ran
    0.74
    elemField
    0.73
     himo
    0.67
    mobileqq
    0.65
    Activations Density 0.004%

    No Known Activations