© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1949
    Prev
    Next
    INDEX
    Explanations

    the verb "draw" used to mean deduce or attract attention

    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
    Not in Any Lists

    No Comments

    Negative Logits
    EndInit
    -0.78
    ContentAsync
    -0.77
    ⓧ
    -0.74
    Välislingid
    -0.73
     tink
    -0.72
    EndGlobalSection
    -0.70
    EndProject
    -0.70
    tagHelperRunner
    -0.69
     shelled
    -0.68
    findpost
    -0.67
    POSITIVE LOGITS
     draw
    3.22
     drawn
    3.20
    draw
    3.05
     Draw
    3.02
     draws
    2.97
     drawing
    2.94
    Draw
    2.86
     drew
    2.84
     DRAW
    2.80
     Draws
    2.77
    Activations Density 0.252%

    No Known Activations