© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 2003
    Prev
    Next
    INDEX
    Explanations

    costs

    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
     Costs
    -1.46
     costs
    -1.45
    Costs
    -1.34
    costs
    -1.30
     COSTS
    -1.23
     expenses
    -1.02
     Expenses
    -0.95
     cost
    -0.91
    expenses
    -0.91
     cup
    -0.87
    POSITIVE LOGITS
    way
    0.50
    บค
    0.44
    وك
    0.43
     biệt
    0.43
    Datuak
    0.43
    ImageContext
    0.42
    lüğ
    0.41
    var
    0.41
    set
    0.40
    вар
    0.40
    Activations Density 0.088%

    No Known Activations