© 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. 46014
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    bels
    -1.46
     Kingdoms
    -1.01
    OGND
    -0.56
    хь
    -0.54
     препратки
    -0.54
     nahilalakip
    -0.52
     CreateTagHelper
    -0.52
    Hauptartikel
    -0.50
     CWE
    -0.50
    levard
    -0.50
    POSITIVE LOGITS
    قایناق‌لار
    0.64
    FileDescriptor
    0.56
    horst
    0.50
    sizeCache
    0.50
    WebServlet
    0.49
    ObjectContext
    0.48
    WebMethod
    0.48
    SqlClient
    0.46
    DataSetChanged
    0.46
    penup
    0.46
    Activations Density 0.046%

    No Known Activations