© 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. 20-CLT-HP
    7. 72583
    Prev
    Next
    INDEX
    Explanations

    Titles like "Director"

    np_max-act-logits · 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
     مشين
    -0.62
    pulumi
    -0.59
    ंदीखरीदारी
    -0.58
     الحره
    -0.57
    thâu
    -0.57
    帖最后由
    -0.53
    Wal
    -0.52
     Wab
    -0.51
    Took
    -0.51
    MLLoader
    -0.50
    POSITIVE LOGITS
     برانيه
    0.60
     Directorate
    0.58
    fu
    0.58
     Director
    0.52
    ản
    0.49
     director
    0.49
    Zdroje
    0.49
     ơn
    0.48
    Bibliografía
    0.48
     DIRECTOR
    0.48
    Activations Density 0.001%

    No Known Activations