© 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. 1490
    Prev
    Next
    INDEX
    Explanations

    the word "look" and its derivatives.

    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
     /\.(
    -0.70
     bezeichneter
    -0.63
    ><!--
    -0.57
    Erich
    -0.54
     /\.
    -0.54
    Statement
    -0.53
     Disqus
    -0.53
     navideña
    -0.52
    getExternal
    -0.51
     mxArray
    -0.51
    POSITIVE LOGITS
     look
    1.01
     Look
    0.99
     LOOK
    0.97
    Look
    0.93
    LOOK
    0.92
     looked
    0.85
    look
    0.85
     looks
    0.85
    looks
    0.79
     Looks
    0.79
    Activations Density 0.182%

    No Known Activations