© 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. 4-CLT-HP
    7. 2264
    Prev
    Next
    INDEX
    Explanations

    terminal

    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
    setVerticalGroup
    -0.58
    tvguidetime
    -0.56
    libatkan
    -0.56
     reposo
    -0.52
     fallu
    -0.51
     Pavia
    -0.50
     uſed
    -0.50
    Попис
    -0.50
    pédie
    -0.50
    ipts
    -0.49
    POSITIVE LOGITS
    IsMutable
    0.64
     BorderRadius
    0.60
    UIControlState
    0.59
     للمعارف
    0.53
    COUVER
    0.52
     crossorigin
    0.48
    eté
    0.47
    InjectAttribute
    0.47
    :✨
    0.46
     grievance
    0.46
    Activations Density 0.020%

    No Known Activations