© 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. 6-RES-MATRYOSHKA-DC
    7. 1274
    Prev
    Next
    INDEX
    Explanations

    words relating to safety and protection

    oai_token-act-pair · gemini-2.0-flash
    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
     CommonModule
    -0.71
     disponibilités
    -0.68
    ="@+
    -0.65
    irmanship
    -0.63
     Mandate
    -0.63
     gim
    -0.62
    HasBeenSet
    -0.61
    labelControl
    -0.58
     Longman
    -0.58
    WithMany
    -0.57
    POSITIVE LOGITS
     protection
    1.94
     protect
    1.82
     Protection
    1.82
     protects
    1.80
     Protect
    1.79
    protection
    1.79
    Protect
    1.77
     protecting
    1.77
     PROTECT
    1.77
    Protection
    1.75
    Activations Density 0.653%

    No Known Activations