© 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. 4-CLT-HP
    7. 4799
    Prev
    Next
    INDEX
    Explanations

    scientific/technical terminology

    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
     propOrder
    -0.69
     démocr
    -0.62
     Immediate
    -0.59
    Immediate
    -0.59
     réguli
    -0.59
     gagné
    -0.56
     bonté
    -0.56
    berdayakan
    -0.56
    direct
    -0.55
     resourceCulture
    -0.55
    POSITIVE LOGITS
    UPAC
    0.57
    potranspiration
    0.53
    PMailer
    0.52
    ActiveRecord
    0.50
     Whence
    0.47
    clusal
    0.47
    LVANIA
    0.47
     castig
    0.46
    richTextPanel
    0.46
     demur
    0.45
    Activations Density 0.004%

    No Known Activations