© 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. 32371
    Prev
    Next
    INDEX
    Explanations

    the name "Marshall" in various contexts

    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
     Miki
    -0.76
     GARD
    -0.73
     Boko
    -0.73
    /*
    -0.73
     жерт
    -0.73
     Mets
    -0.71
     streaks
    -0.71
    Feet
    -0.70
     Abra
    -0.69
    CreateMap
    -0.69
    POSITIVE LOGITS
     Marshall
    1.86
    Marshall
    1.70
     MARSHALL
    1.59
     marshall
    1.55
     Marshal
    1.53
    Marshal
    1.36
     marshal
    1.34
    marshall
    1.23
     marsh
    1.22
    Marshaller
    1.22
    Activations Density 0.003%

    No Known Activations