© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13397
    Prev
    Next
    INDEX
    Explanations

    major

    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
     major
    -0.61
    major
    -0.58
     MAJOR
    -0.52
    iolis
    -0.52
    ATURES
    -0.52
     Liar
    -0.51
    Major
    -0.50
     Akismet
    -0.50
    ients
    -0.50
     Major
    -0.49
    POSITIVE LOGITS
    endregion
    0.64
    webElement
    0.62
     vertes
    0.56
    windowFixed
    0.56
     WaitForSeconds
    0.56
    Domains
    0.55
    ImageContext
    0.55
    XmlAccessorType
    0.54
     SafeMath
    0.54
     contextLoads
    0.54
    Activations Density 0.057%

    No Known Activations