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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19642
    Prev
    Next
    INDEX
    Explanations

    references to the Docker platform and its commands

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.98
    enumi
    -0.96
    parsedMessage
    -0.92
     mergeFrom
    -0.85
    kegaard
    -0.84
     Obed
    -0.82
    
    -0.81
    enderror
    -0.81
     mAh
    -0.81
     Мексичка
    -0.79
    POSITIVE LOGITS
    docker
    1.20
     Dock
    1.17
     dock
    1.02
     docker
    1.02
     docking
    1.00
     Docker
    0.96
    Docker
    0.94
    DOCK
    0.92
    Dock
    0.91
    dock
    0.91
    Activations Density 0.003%

    No Known Activations