© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38316
    Prev
    Next
    INDEX
    Explanations

    hang

    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
     hang
    -2.77
     hung
    -2.66
     hangs
    -2.55
     hanging
    -2.45
    hanging
    -2.28
     Hanging
    -2.28
     HANG
    -2.22
    Hanging
    -2.19
     Hang
    -1.99
    Hang
    -1.98
    POSITIVE LOGITS
    OGND
    0.53
    ($__
    0.52
     up
    0.52
    Kjelder
    0.50
    ┏
    0.50
    set
    0.50
    hless
    0.50
    gggg
    0.49
     laaj
    0.49
    طلاق
    0.49
    Activations Density 0.042%

    No Known Activations