© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 10831
    Prev
    Next
    INDEX
    Explanations

    references to wool and woolen textiles

    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
     hotfix
    -0.64
     препратки
    -0.60
    ligators
    -0.55
    EndInit
    -0.53
    Παραπομπές
    -0.53
     ArrayAdapter
    -0.53
    setContentType
    -0.52
     ukra
    -0.52
    STICK
    -0.50
     Galile
    -0.50
    POSITIVE LOGITS
     Wool
    3.69
    Wool
    3.28
     wool
    2.72
    wool
    2.66
     woolen
    1.31
    ウール
    1.27
     woollen
    1.18
     laine
    1.13
     шер
    0.99
     ウール
    0.87
    Activations Density 0.001%

    No Known Activations