© 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. 94162
    Prev
    Next
    INDEX
    Explanations

    cost per person

    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
     budget
    -1.08
    budget
    -0.88
     فريبيس
    -0.80
     budgetary
    -0.80
     budgeting
    -0.75
     BUDGET
    -0.73
     budgets
    -0.69
    findpost
    -0.69
     kasarigan
    -0.68
    Budget
    -0.67
    POSITIVE LOGITS
    boten
    0.65
    ged
    0.53
    FACTS
    0.52
     Sign
    0.52
    TextSpan
    0.52
     isInitialized
    0.51
    ंदीखरीदारी
    0.50
     jLabel
    0.50
    esModule
    0.48
    Faster
    0.48
    Activations Density 0.983%

    No Known Activations