© 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. 140
    Prev
    Next
    INDEX
    Explanations

    speed

    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
     swift
    -0.58
     rapidly
    -0.58
     fast
    -0.58
     swiftly
    -0.56
    χύ
    -0.53
     sudden
    -0.53
     Sudden
    -0.52
     rapid
    -0.52
    licky
    -0.52
     kunjung
    -0.51
    POSITIVE LOGITS
    kmäler
    0.70
     виправивши
    0.67
    SpringRunner
    0.54
     largely
    0.50
    合わせた
    0.48
    Література
    0.48
    MockBean
    0.47
    makeText
    0.47
    mêmes
    0.46
     puesta
    0.46
    Activations Density 0.002%

    No Known Activations