© 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. 0-CLT-HP
    7. 92302
    Prev
    Next
    INDEX
    Explanations

    code or names

    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
    bru
    -0.62
    ioli
    -0.57
     Hons
    -0.56
    TagMode
    -0.50
    brum
    -0.50
     بند
    -0.48
     vektör
    -0.47
     gloire
    -0.46
    DeclareMath
    -0.46
    DebuggerNonUser
    -0.46
    POSITIVE LOGITS
     TestBed
    0.62
     EClass
    0.61
    Anhalt
    0.60
    رشف
    0.59
    PyExc
    0.57
    хь
    0.56
     Приступљено
    0.56
    
    0.56
    InSection
    0.56
    EndInit
    0.55
    Activations Density 0.249%

    No Known Activations