© 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. 1-CLT-HP
    7. 46168
    Prev
    Next
    INDEX
    Explanations

    Thule

    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
     GenerationType
    -0.75
    adaptiveStyles
    -0.56
     lenker
    -0.52
    billon
    -0.52
    jbl
    -0.51
    ‍♂️
    -0.50
    –¿
    -0.47
    PasswordEncoder
    -0.46
    knex
    -0.46
     Chum
    -0.45
    POSITIVE LOGITS
    SuppressMessage
    0.56
    AddTagHelper
    0.54
    XmlAccessorType
    0.53
     الاطلاع
    0.53
    webElementXpaths
    0.52
    OGND
    0.51
    ิ้ง
    0.51
     Reap
    0.51
     Head
    0.50
    ParallelGroup
    0.50
    Activations Density 0.008%

    No Known Activations