© 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. 1-RES-MATRYOSHKA-DC
    7. 1221
    Prev
    Next
    INDEX
    Explanations

    words describing exceptional quality or admiration, such as "amazing."

    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
    Not in Any Lists

    No Comments

    Negative Logits
     cierta
    -0.59
     trebui
    -0.57
    jmniej
    -0.57
    PostConstruct
    -0.56
     Liked
    -0.56
     Erişim
    -0.56
    较为
    -0.56
     agak
    -0.56
    とはいえ
    -0.54
    早めに
    -0.53
    POSITIVE LOGITS
     amazing
    3.02
     incredible
    2.89
    amazing
    2.73
    incredible
    2.52
     AMAZING
    2.45
    Amazing
    2.44
     marvelous
    2.42
     stunning
    2.41
     astounding
    2.41
     Amazing
    2.39
    Activations Density 0.977%

    No Known Activations