© 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. 12-RES-MATRYOSHKA-DC
    7. 23468
    Prev
    Next
    INDEX
    Explanations

    references to military units or forces

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    ymce
    -0.84
     Ples
    -0.79
     Egl
    -0.77
     للمعارف
    -0.75
    KOM
    -0.73
     Giz
    -0.73
     ople
    -0.73
     Ech
    -0.71
     Healey
    -0.70
    bestos
    -0.68
    POSITIVE LOGITS
     Guard
    1.41
     Guards
    1.34
     GUARD
    1.34
     guard
    1.26
    Guard
    1.23
     guards
    1.20
    Guards
    1.18
    GUARD
    1.09
    guard
    0.97
    AuthGuard
    0.95
    Activations Density 0.011%

    No Known Activations