© 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. 28019
    Prev
    Next
    INDEX
    Explanations

    chemical bonding structures and interactions in organic compounds

    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
    RetentionPolicy
    -0.88
     propOrder
    -0.84
    ########.
    -0.75
    AsUp
    -0.73
    ագրություններ
    -0.72
    migrationBuilder
    -0.71
     تضيفلها
    -0.70
    __":
    -0.68
    település
    -0.68
    ]--;
    -0.67
    POSITIVE LOGITS
     ResponseEntity
    0.50
     SDLK
    0.50
    Passcode
    0.50
     Lana
    0.48
     depender
    0.48
     carbon
    0.47
     onions
    0.47
     PUN
    0.47
     umowy
    0.47
     Landis
    0.47
    Activations Density 0.023%

    No Known Activations