© 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. 1483
    Prev
    Next
    INDEX
    Explanations

    mentions of watching or observing something, often in conjunction with people

    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
    oprot
    -0.56
    mahaman
    -0.54
    pez
    -0.53
     gevoel
    -0.53
     Into
    -0.52
     knowing
    -0.52
     AppBundle
    -0.52
     bilin
    -0.51
    ึ่ง
    -0.50
     oublier
    -0.50
    POSITIVE LOGITS
     firsthand
    0.92
     unfold
    0.80
     atenta
    0.71
    👀
    0.69
     👀
    0.68
     вжи
    0.66
     referenties
    0.65
     TestBed
    0.65
     closely
    0.64
     attentively
    0.64
    Activations Density 1.102%

    No Known Activations