© 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. 6844
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "disruption" or related terms indicating interference or disturbance

    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
    CodeAttribute
    -0.58
     Sagan
    -0.57
    DeleteBehavior
    -0.57
    kul
    -0.56
    новниш
    -0.56
    kräf
    -0.56
     argv
    -0.54
     Moran
    -0.54
     dirait
    -0.52
     tauto
    -0.51
    POSITIVE LOGITS
     disturbance
    2.33
     disruption
    2.23
     disturb
    2.20
     disturbed
    2.14
     disturbances
    2.14
     Disturb
    2.11
     disrupt
    2.09
     disrupted
    2.09
     disruptions
    2.06
     disrupting
    2.05
    Activations Density 0.109%

    No Known Activations