© 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. 2-RES-MATRYOSHKA-DC
    7. 7553
    Prev
    Next
    INDEX
    Explanations

    words or references indicating something with high intensity or strength

    oai_token-act-pair · gpt-4.1-nano
    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
    淡
    -0.57
     جز
    -0.52
     dry
    -0.51
    Link
    -0.49
     twinkle
    -0.49
     رمز
    -0.49
     Petron
    -0.48
     <=",
    -0.48
     light
    -0.48
     Италијани
    -0.48
    POSITIVE LOGITS
     powerful
    2.67
    powerful
    2.63
     Powerful
    2.56
    Powerful
    2.55
     puissante
    2.20
     puissant
    2.13
     poderoso
    1.98
     poderosa
    1.92
     poderosos
    1.92
     potente
    1.90
    Activations Density 0.044%

    No Known Activations