© 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. 5-CLT-HP
    7. 3620
    Prev
    Next
    INDEX
    Explanations

    kitchen

    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
    sä
    -0.50
     informée
    -0.47
     متعلقه
    -0.47
     لينك
    -0.44
     Eisenbahn
    -0.44
     immunotherapy
    -0.43
     uParam
    -0.43
     Hansen
    -0.43
     userDetails
    -0.42
     lateinit
    -0.41
    POSITIVE LOGITS
     cooking
    0.69
    niająca
    0.65
     Cooking
    0.64
     betweenstory
    0.61
    Cooking
    0.61
    LabelTagHelper
    0.61
    interopRequire
    0.61
     Réponses
    0.59
    awtextra
    0.58
    Personensuche
    0.58
    Activations Density 0.001%

    No Known Activations