© 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. 22-RES-MATRYOSHKA-DC
    7. 3276
    Prev
    Next
    INDEX
    Explanations

    words and phrases about being part of things

    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
    Negative Logits
    EndInit
    -0.57
     among
    -0.57
     within
    -0.54
     chez
    -0.53
    among
    -0.50
     dentro
    -0.50
     binnen
    -0.49
    within
    -0.49
     среди
    -0.49
     between
    -0.49
    POSITIVE LOGITS
     actively
    0.87
     propOrder
    0.84
     createState
    0.81
    UseVisualStyle
    0.77
    =$?
    0.71
     aktif
    0.70
     engaged
    0.69
    tvguidetime
    0.69
    PositiveButton
    0.68
     فريبيس
    0.68
    Activations Density 0.161%

    No Known Activations