© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1366
    Prev
    Next
    INDEX
    Explanations

    the task-related section of a technical document

    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
    Negative Logits
    شوف
    -0.67
    بوابة
    -0.66
    contentLoaded
    -0.66
    NUMX
    -0.59
     '\\;'
    -0.59
    everybody
    -0.59
    ViewImports
    -0.58
    Chham
    -0.58
     onlyOwner
    -0.57
     melay
    -0.56
    POSITIVE LOGITS
     task
    4.59
    task
    4.13
     Task
    4.06
    Task
    4.00
     tasks
    3.70
     TASK
    3.63
     Tasks
    3.53
    TASK
    3.44
    tasks
    3.41
    Tasks
    3.23
    Activations Density 0.227%

    No Known Activations