© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45628
    Prev
    Next
    INDEX
    Explanations

    transplants and adsorption

    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
     adsorption
    -0.71
     Adsorption
    -0.64
     adsor
    -0.56
    <bos>
    -0.52
     propOrder
    -0.52
    pushFollow
    -0.51
    Gotcha
    -0.50
     surla
    -0.50
    qrst
    -0.50
     sorption
    -0.50
    POSITIVE LOGITS
    öglichkeiten
    0.57
     ویکی‌پدیا
    0.57
    (!__
    0.56
    contentLoaded
    0.56
    CardBody
    0.49
    MemoryWarning
    0.49
    ':
    0.49
    onavirus
    0.48
    }{*}{
    0.48
    hejiang
    0.48
    Activations Density 0.082%

    No Known Activations