© 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. 2719
    Prev
    Next
    INDEX
    Explanations

    urgency

    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
     originaux
    -0.65
     flesta
    -0.63
     виправивши
    -0.60
     barnen
    -0.60
     stället
    -0.59
     baratas
    -0.57
     ainfi
    -0.57
     spesa
    -0.55
     genoemd
    -0.54
     fallu
    -0.54
    POSITIVE LOGITS
     and
    0.66
    GOTREF
    0.65
     recognizable
    0.62
    Билгалдахарш
    0.62
     obvious
    0.59
     stopping
    0.59
     instant
    0.58
    ็จ
    0.57
    TagMode
    0.57
    MemoryWarning
    0.56
    Activations Density 0.001%

    No Known Activations