© 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. 1-CLT-HP
    7. 14033
    Prev
    Next
    INDEX
    Explanations

    sacred/holy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tanleria
    -0.85
    FormTagHelper
    -0.85
     typelib
    -0.82
     resourceCulture
    -0.77
    sacred
    -0.74
     kaynağından
    -0.74
    rungsseite
    -0.73
    ThroughAttribute
    -0.71
     Wikimedijinoj
    -0.71
     للمعارف
    -0.70
    POSITIVE LOGITS
     Hindu
    0.52
     place
    0.45
     civil
    0.43
     Muslim
    0.42
     tree
    0.42
    ग
    0.41
     ground
    0.41
     animal
    0.40
    JpaRepository
    0.40
    vertra
    0.39
    Activations Density 0.003%

    No Known Activations