© 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. 15583
    Prev
    Next
    INDEX
    Explanations

    commands or signals related to disabling or turning off a device or feature

    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
    MigrationBuilder
    -0.97
     itſelf
    -0.95
     poffe
    -0.85
     ſeveral
    -0.85
     quæ
    -0.84
     avoient
    -0.84
     ſtate
    -0.82
     habet
    -0.82
     étoient
    -0.82
     HasFactory
    -0.81
    POSITIVE LOGITS
    disable
    1.27
    xc
    0.53
     InputDecoration
    0.51
    lec
    0.46
    oog
    0.46
     Barr
    0.46
     alak
    0.44
     stock
    0.43
     Guil
    0.43
    utnik
    0.42
    Activations Density 0.010%

    No Known Activations