© 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. 0-RES-MATRYOSHKA-DC
    7. 10419
    Prev
    Next
    INDEX
    Explanations

    snippets of code related to controlling hardware components

    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
    MigrationBuilder
    -0.77
    ValueStyle
    -0.74
     Efq
    -0.72
    UrlResolution
    -0.65
    DeleteBehavior
    -0.64
    InteropServices
    -0.63
     Monfieur
    -0.63
    AntiForgeryToken
    -0.61
     itſelf
    -0.60
    viewWillAppear
    -0.60
    POSITIVE LOGITS
    control
    1.56
    Control
    0.80
    CONTROL
    0.70
    -------
    0.56
    __':
    0.53
    templateUrl
    0.52
     nonatomic
    0.51
    inib
    0.50
    __":
    0.49
    COLN
    0.49
    Activations Density 0.006%

    No Known Activations