© 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. 12210
    Prev
    Next
    INDEX
    Explanations

    Michael

    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
     Michael
    -1.50
    Michael
    -1.43
     michael
    -1.13
    michael
    -1.04
    MICHAEL
    -0.95
     MICHAEL
    -0.93
     Michaels
    -0.66
     Miche
    -0.61
    micha
    -0.54
     baseline
    -0.51
    POSITIVE LOGITS
     يتيمه
    0.80
    PerformLayout
    0.78
    OGND
    0.71
    Portail
    0.71
     незавершена
    0.69
    /**
    0.66
     EconPapers
    0.65
     Roskov
    0.65
    EndInit
    0.64
    الحياه
    0.64
    Activations Density 0.011%

    No Known Activations