© 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. 15606
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "disruption."

    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
     interrupt
    -1.56
     interrupted
    -1.53
     interrupts
    -1.33
     Interrupt
    -1.21
     interrupting
    -1.10
     interruption
    -1.03
    interrupt
    -1.02
    interrupted
    -0.97
    Interrupt
    -0.84
     interruptions
    -0.83
    POSITIVE LOGITS
     disruption
    1.62
     disrupt
    1.28
     disrupting
    1.26
     disruptive
    1.23
     disruptions
    1.21
     disrupted
    1.20
    押
    0.48
     reaſon
    0.48
     création
    0.48
     creation
    0.47
    Activations Density 0.006%

    No Known Activations