© 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. 1632
    Prev
    Next
    INDEX
    Explanations

    the verb "take" followed by a preposition or article.

    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
    存于互联网档案馆
    -0.67
    rdı
    -0.63
     Wikimedijinoj
    -0.60
    Cordialement
    -0.59
     незавершена
    -0.59
     onBind
    -0.58
    VERTISEMENT
    -0.58
    Portály
    -0.57
    ^(@)
    -0.57
    críbete
    -0.55
    POSITIVE LOGITS
     advantage
    1.13
     care
    1.09
    take
    1.07
    took
    1.06
    Taking
    1.06
    Take
    1.02
     take
    1.00
    Takes
    0.98
    Took
    0.98
     Taking
    0.96
    Activations Density 0.601%

    No Known Activations