© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 934
    Prev
    Next
    INDEX
    Explanations

    words related to the study of stars in the Taurus constellation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Woodford
    -0.67
     protoimpl
    -0.61
    +#+
    -0.53
     chi̍t
    -0.52
     Borden
    -0.52
    RetentionPolicy
    -0.50
    eradish
    -0.50
    urlencoded
    -0.50
    warzys
    -0.49
    typeparam
    -0.49
    POSITIVE LOGITS
     stars
    2.17
     star
    2.09
     Stars
    2.05
    stars
    1.95
    Stars
    1.86
     Star
    1.83
     STARS
    1.80
    star
    1.73
    Star
    1.73
     STAR
    1.61
    Activations Density 0.513%

    No Known Activations