© 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. 32348
    Prev
    Next
    INDEX
    Explanations

    references to actors and their roles

    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
     picioare
    -0.80
    pendientes
    -0.73
     Willen
    -0.73
    omethane
    -0.72
     Hollis
    -0.72
     rând
    -0.71
     hini
    -0.68
     nivelul
    -0.67
     Schnell
    -0.66
    through
    -0.65
    POSITIVE LOGITS
     Actors
    1.49
     actors
    1.36
     actor
    1.34
     Actor
    1.31
    Actors
    1.27
    Actor
    1.10
    actors
    1.10
     Actress
    1.09
    actor
    1.04
     actress
    1.02
    Activations Density 0.006%

    No Known Activations