© 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. 3180
    Prev
    Next
    INDEX
    Explanations

    against

    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
     فريبيس
    -0.54
    ագրություններ
    -0.51
    RTEX
    -0.50
    ViewFeatures
    -0.48
    EndGlobalSection
    -0.46
    hyrchwyd
    -0.43
     hopelessly
    -0.42
     daqui
    -0.40
     nia
    -0.39
     Constipation
    -0.39
    POSITIVE LOGITS
    下载附件
    0.74
    +#+
    0.72
     pinulongan
    0.65
    validates
    0.65
    úgó
    0.64
    település
    0.63
    出版年
    0.63
     nonatomic
    0.62
    ftagPool
    0.60
    kloped
    0.60
    Activations Density 0.000%

    No Known Activations