© 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. 605
    Prev
    Next
    INDEX
    Explanations

    words or phrases signifying prevention, inhibition, or obstruction.

    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
     Gracia
    -0.60
     урна
    -0.59
    арак
    -0.55
     Besoin
    -0.55
     vertes
    -0.54
     Aguilera
    -0.51
    namentales
    -0.50
     tere
    -0.50
    mények
    -0.49
    Feuer
    -0.49
    POSITIVE LOGITS
     blocking
    1.80
     block
    1.78
     blocks
    1.75
     Prevent
    1.75
     BLOCK
    1.74
     Block
    1.72
     prevent
    1.71
     stops
    1.70
     blocked
    1.70
     preventing
    1.70
    Activations Density 0.897%

    No Known Activations