© 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. 22-RES-MATRYOSHKA-DC
    7. 907
    Prev
    Next
    INDEX
    Explanations

    the word "do" or "doing" preceded by a preposition or modal verb

    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
    glBegin
    -0.62
     mxArray
    -0.52
    brainly
    -0.50
    ありますか
    -0.50
    beginPath
    -0.49
    ăzi
    -0.48
    buie
    -0.48
     ترین
    -0.47
    fortawesome
    -0.47
    +#+#
    -0.47
    POSITIVE LOGITS
     so
    3.89
    so
    2.80
    So
    2.48
     So
    2.39
     så
    2.22
    所以
    2.09
     così
    2.05
     так
    1.90
     SO
    1.87
     sehingga
    1.80
    Activations Density 2.074%

    No Known Activations