© 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. 2-RES-MATRYOSHKA-DC
    7. 7384
    Prev
    Next
    INDEX
    Explanations

    segments of structured code involving resource identifiers and API operations

    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
     MainAxisSize
    -0.79
    RegressionTest
    -0.76
     GenerationType
    -0.70
     الحره
    -0.66
     باخ
    -0.66
    UnsafeEnabled
    -0.62
     كومونز
    -0.61
    djangoproject
    -0.60
     ContentValues
    -0.59
     للمعارف
    -0.57
    POSITIVE LOGITS
    mbor
    0.49
    CustomerID
    0.45
    psum
    0.45
    eadas
    0.45
    risse
    0.44
     SSR
    0.44
    kian
    0.44
     septembrie
    0.44
     QtGui
    0.43
    ünkü
    0.43
    Activations Density 1.111%

    No Known Activations