© 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. 0-RES-MATRYOSHKA-DC
    7. 15643
    Prev
    Next
    INDEX
    Explanations

    references to the concept of quality or excellence

    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
     оригіналу
    -0.69
     виправивши
    -0.63
    ništvo
    -0.63
    esez
    -0.59
     solito
    -0.59
    født
    -0.58
    Espèce
    -0.57
     ویکی‌پدیای
    -0.57
     proprement
    -0.56
     Мексичка
    -0.56
    POSITIVE LOGITS
    RegistryLite
    0.63
    ontes
    0.55
    Buildable
    0.53
    {}
    0.53
    GraphicsUnit
    0.52
     Knapp
    0.52
    __()
    0.51
    ViewHolder
    0.51
     Initialized
    0.50
    firestore
    0.50
    Activations Density 0.423%

    No Known Activations