© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 1603
    Prev
    Next
    INDEX
    Explanations

    instances of the word "can"

    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.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    Попис
    -0.93
    libft
    -0.82
    ########.
    -0.82
    WriteTagHelper
    -0.80
    bootstrapcdn
    -0.79
     للمعارف
    -0.78
     ModelExpression
    -0.74
    dafx
    -0.73
    ThroughAttribute
    -0.73
     MainAxisSize
    -0.71
    POSITIVE LOGITS
     easily
    0.75
     facilmente
    0.62
     facilement
    0.61
     легко
    0.58
     afford
    0.56
    Easily
    0.55
     cant
    0.54
    easily
    0.54
     Easily
    0.54
     CAN
    0.52
    Activations Density 0.548%

    No Known Activations