© 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. 5-CLT-HP
    7. 3007
    Prev
    Next
    INDEX
    Explanations

    vegetables

    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
     Audiodateien
    -0.64
    RegressionTest
    -0.63
     CreateTagHelper
    -0.60
    webElementXpaths
    -0.60
    脚注の使い方
    -0.59
     pinulongan
    -0.58
     Normdatei
    -0.57
     nahilalakip
    -0.56
     MonoBehaviour
    -0.56
     Dunes
    -0.55
    POSITIVE LOGITS
     ujednoznacz
    0.50
     citrus
    0.48
    Citrus
    0.47
    apple
    0.47
    mil
    0.45
    vě
    0.45
    فا
    0.44
    ivat
    0.44
     grapefruit
    0.43
    Fruit
    0.43
    Activations Density 0.001%

    No Known Activations