© 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. 0-CLT-HP
    7. 92984
    Prev
    Next
    INDEX
    Explanations

    budget

    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
    -1.91
     Budget
    -1.68
    Budget
    -1.66
    budget
    -1.63
     BUDGET
    -1.60
     budgets
    -1.53
     Budgets
    -1.42
     budgetary
    -1.38
     budgeting
    -1.27
    BUDGET
    -1.24
    POSITIVE LOGITS
    फल
    0.46
    ural
    0.45
    elerik
    0.44
    ch
    0.41
    WebMethod
    0.40
     redor
    0.39
    setOnItem
    0.39
     on
    0.39
    tery
    0.39
     ở
    0.38
    Activations Density 0.070%

    No Known Activations