© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1897
    Prev
    Next
    INDEX
    Explanations

    narratives around ship-related events, often mentioning dates, locations, and naval terminology

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     correctes
    -0.63
    kmäler
    -0.53
    ANTLR
    -0.52
    ьаж
    -0.52
     otomatig
    -0.51
     okuyayım
    -0.50
    Démographie
    -0.50
    ayette
    -0.50
     NSCoder
    -0.50
    ρούν
    -0.49
    POSITIVE LOGITS
     ship
    1.69
     boat
    1.55
     sailing
    1.50
     ships
    1.49
     boats
    1.47
     vessel
    1.43
     sail
    1.42
     sailed
    1.37
     Ship
    1.34
     maritime
    1.34
    Activations Density 1.340%

    No Known Activations