© 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. 25325
    Prev
    Next
    INDEX
    Explanations

    references to locked doors and the actions surrounding them

    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
     للمعارف
    -0.64
    ScopeManager
    -0.60
     Davi
    -0.56
    MemoryWarning
    -0.54
     CreateTagHelper
    -0.54
     Davie
    -0.54
     Withdrawal
    -0.54
     Withdraw
    -0.53
     cliffs
    -0.53
     Viva
    -0.53
    POSITIVE LOGITS
     door
    0.71
    HomeAsUpEnabled
    0.64
    door
    0.61
     pintu
    0.61
     doors
    0.60
    JpaRepository
    0.59
     puerta
    0.58
    puerta
    0.58
    phide
    0.57
     burglary
    0.57
    Activations Density 0.041%

    No Known Activations