© 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. 4673
    Prev
    Next
    INDEX
    Explanations

    events

    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
    rawDesc
    -0.68
     itſelf
    -0.66
    źni
    -0.64
     themſelves
    -0.64
     ſhe
    -0.63
    出版年
    -0.62
    ChildScrollView
    -0.62
    ::_('
    -0.61
     raiſ
    -0.59
     MUT
    -0.58
    POSITIVE LOGITS
     resourceCulture
    0.63
     :
    0.63
    :
    0.61
     مشين
    0.58
    Искәрмәләр
    0.50
    Šaltiniai
    0.49
    simpleType
    0.48
    ：
    0.48
     esternos
    0.47
    EndContext
    0.47
    Activations Density 0.014%

    No Known Activations