© 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. 3071
    Prev
    Next
    INDEX
    Explanations

    personal characteristics

    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
    :✨
    -0.66
    vermectin
    -0.58
    ergies
    -0.53
     Capri
    -0.50
    bic
    -0.50
    TagMode
    -0.50
     Penh
    -0.49
    ELTS
    -0.49
    سطس
    -0.48
    och
    -0.48
    POSITIVE LOGITS
     about
    0.58
    stretchr
    0.54
    expandindo
    0.54
     المعيارى
    0.52
    MessageOf
    0.50
     menahan
    0.49
    ousands
    0.47
    MessageTagHelper
    0.47
     ProtoMessage
    0.47
     surround
    0.46
    Activations Density 0.000%

    No Known Activations