© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 5422
    Prev
    Next
    INDEX
    Explanations

    the word "stop" and its variations 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
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.90
     Huxley
    -0.88
    %
    
    -0.87
     Allociné
    -0.83
    Württemberg
    -0.81
    ="#"><
    -0.81
    hydrates
    -0.80
     للمعارف
    -0.80
     Henley
    -0.79
     Fichier
    -0.78
    POSITIVE LOGITS
     stops
    1.56
     stop
    1.54
     STOP
    1.53
     Stop
    1.47
     Stops
    1.47
    stop
    1.46
    Stop
    1.40
    stops
    1.40
    STOP
    1.39
    Stops
    1.32
    Activations Density 0.061%

    No Known Activations