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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5173
    Prev
    Next
    INDEX
    Explanations

    onga

    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
     engraçadas
    -0.65
    ərbaycan
    -0.60
    styleType
    -0.58
     varandra
    -0.57
    Viki
    -0.56
    }{#
    -0.55
     himo
    -0.55
     purpoſe
    -0.54
    afone
    -0.54
     Anſ
    -0.53
    POSITIVE LOGITS
    rias
    0.50
    TestingModule
    0.50
     rospy
    0.49
     UserDao
    0.48
    setVerticalGroup
    0.48
     CommonModule
    0.47
    listdir
    0.46
    DoubleQuotes
    0.46
     inspired
    0.45
    ">//
    0.45
    Activations Density 0.000%

    No Known Activations