© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4527
    Prev
    Next
    INDEX
    Explanations

    arrival

    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
     تضيفلها
    -0.65
    ppins
    -0.63
    ceedings
    -0.49
    出版年
    -0.48
    enee
    -0.47
    anabe
    -0.46
    coming
    -0.45
     Taktlose
    -0.45
     超
    -0.44
    attan
    -0.43
    POSITIVE LOGITS
     pinulongan
    0.76
    tagext
    0.68
    MemoryWarning
    0.68
     in
    0.65
    WebServlet
    0.63
     AssemblyVersion
    0.60
     XHTML
    0.59
     Familienname
    0.56
    Rüyada
    0.56
     DAK
    0.55
    Activations Density 0.011%

    No Known Activations