© 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. 159
    Prev
    Next
    INDEX
    Explanations

    detection

    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
     MainAxisSize
    -0.59
    ModelMap
    -0.55
     typelib
    -0.54
     doGet
    -0.50
    assertNotNull
    -0.49
    djangoproject
    -0.49
     betweenstory
    -0.48
    RegressionTest
    -0.45
     esternos
    -0.45
     jegy
    -0.44
    POSITIVE LOGITS
     amounts
    0.82
     levels
    0.75
     الحره
    0.71
     amount
    0.69
    amounts
    0.64
    BeginContext
    0.60
     (<
    0.57
     Amounts
    0.57
     quantities
    0.57
     وتسجيلات
    0.56
    Activations Density 0.004%

    No Known Activations