© 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. 269
    Prev
    Next
    INDEX
    Explanations

    joined

    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
    BeginInit
    -0.48
     Soviet
    -0.46
    WriteTagHelper
    -0.46
    thâu
    -0.45
     invokevirtual
    -0.45
    olved
    -0.44
    modelBuilder
    -0.44
     оригіналу
    -0.44
    idium
    -0.43
     émotion
    -0.43
    POSITIVE LOGITS
    PreferredItem
    0.73
    WebMethod
    0.58
    gbaar
    0.55
    TagMode
    0.54
     Drink
    0.53
     SwiftUI
    0.52
    UIControlState
    0.51
    ⓘ
    0.49
    aspectj
    0.48
     bParam
    0.48
    Activations Density 0.001%

    No Known Activations