© 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. 12-RES-MATRYOSHKA-DC
    7. 28513
    Prev
    Next
    INDEX
    Explanations

    instances of the word "browse" and its variations, indicating a focus on browsing activities

    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
     stadiums
    -0.77
     estimés
    -0.75
     onAnimation
    -0.71
    ⓧ
    -0.70
     Englishmen
    -0.68
     doccia
    -0.67
     decathlon
    -0.65
    DoubleQuotes
    -0.63
     événement
    -0.62
     Xperia
    -0.62
    POSITIVE LOGITS
     browse
    1.55
     Browse
    1.42
    browse
    1.40
     browsing
    1.39
    Browse
    1.36
     Brows
    1.33
    brows
    1.18
    Brows
    1.09
     BROW
    1.00
     brows
    0.91
    Activations Density 0.006%

    No Known Activations