© 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. 3-RES-MATRYOSHKA-DC
    7. 3213
    Prev
    Next
    INDEX
    Explanations

    the word "capture".

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     cap
    -0.76
    cap
    -0.71
     Supremo
    -0.65
    CAP
    -0.60
     Caps
    -0.59
     caps
    -0.57
     Capac
    -0.57
     CAP
    -0.56
    :][
    -0.54
     capacity
    -0.52
    POSITIVE LOGITS
     capture
    2.75
     Capture
    2.59
     captured
    2.58
     captures
    2.55
     capturing
    2.42
    capture
    2.33
    Capture
    2.28
    captured
    2.27
    Captured
    1.98
     captur
    1.96
    Activations Density 0.028%

    No Known Activations