© 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-CLT-HP
    7. 95033
    Prev
    Next
    INDEX
    Explanations

    Business and technical jargon

    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
     management
    -1.18
    management
    -1.05
     manajemen
    -0.97
     Management
    -0.96
    Management
    -0.90
     MANAGEMENT
    -0.88
    __":
    -0.83
    MANAGEMENT
    -0.80
     gestione
    -0.77
    帖最后由
    -0.74
    POSITIVE LOGITS
    المناصب
    0.56
     للمعارف
    0.52
     grids
    0.50
     archae
    0.49
     eventdata
    0.49
    ьаж
    0.49
     itſelf
    0.49
     Reſ
    0.48
    ftagPool
    0.48
     vermogen
    0.47
    Activations Density 0.156%

    No Known Activations