© 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. 1342
    Prev
    Next
    INDEX
    Explanations

    variations of the word "search"

    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
    Tikang
    -0.79
    ########.
    -0.78
    CopyWith
    -0.77
    ViewFeatures
    -0.67
    GeneratedCode
    -0.63
     newOwner
    -0.59
     فريبيس
    -0.59
     Clem
    -0.58
    átula
    -0.58
     Hotspur
    -0.58
    POSITIVE LOGITS
     Search
    1.06
     SEARCH
    1.02
    SEARCH
    0.98
     搜索
    0.97
     Searches
    0.96
     search
    0.93
     searches
    0.89
    Search
    0.88
     Searching
    0.86
     Sear
    0.85
    Activations Density 0.167%

    No Known Activations