© 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. 2863
    Prev
    Next
    INDEX
    Explanations

    Dates and times

    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
     disambiguazione
    -0.65
    ंदीखरीदारी
    -0.54
    <bos>
    -0.53
    ).
    -0.50
    ViewFeatures
    -0.50
     oprot
    -0.49
     ...)
    -0.49
     ويكيميديا
    -0.49
    ...)
    -0.48
    WithIOException
    -0.48
    POSITIVE LOGITS
    OGND
    0.64
    ruary
    0.56
     yesterday
    0.56
    出版年
    0.55
    esterday
    0.54
    Kaynakça
    0.53
    Izvori
    0.50
     IndexPath
    0.49
    yesterday
    0.49
     Saturday
    0.48
    Activations Density 0.036%

    No Known Activations