© 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. 6-RES-MATRYOSHKA-DC
    7. 1602
    Prev
    Next
    INDEX
    Explanations

    words relating to physical movement, often including direction

    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
     HasFactory
    -0.66
     Britt
    -0.60
     peggio
    -0.59
    Britt
    -0.58
    GEBURTSDATUM
    -0.58
    Bij
    -0.57
     }</
    -0.57
    bao
    -0.57
    (|
    -0.56
    carat
    -0.56
    POSITIVE LOGITS
     moves
    2.05
     move
    2.02
     Move
    2.02
     moved
    1.99
     Moves
    1.98
     MOVE
    1.98
     moving
    1.93
     Moving
    1.90
    Moving
    1.85
     MOVING
    1.85
    Activations Density 0.435%

    No Known Activations