© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4570
    Prev
    Next
    INDEX
    Explanations

    the multiple meanings and contexts related to the word "way."

    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
     méthode
    -0.99
    methods
    -0.90
     pleaſure
    -0.90
     Method
    -0.89
    getMethod
    -0.89
     noël
    -0.88
     uſed
    -0.88
     methods
    -0.87
     metode
    -0.87
     hasard
    -0.86
    POSITIVE LOGITS
    way
    0.88
    WAY
    0.79
     WAY
    0.79
     way
    0.73
     Way
    0.69
    Way
    0.69
     Wayback
    0.69
     pira
    0.69
    ViewFeatures
    0.67
     Voy
    0.67
    Activations Density 0.056%

    No Known Activations