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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5605
    Prev
    Next
    INDEX
    Explanations

    Setting context

    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
    ,
    -0.65
    StoreMessageInfo
    -0.56
    новништво
    -0.52
     belangrij
    -0.50
    inyin
    -0.50
    ricians
    -0.49
     to
    -0.49
    localctx
    -0.48
     desembar
    -0.47
     Вікі
    -0.46
    POSITIVE LOGITS
    enumi
    0.66
     ویکی‌پدیای
    0.63
     وتسجيلات
    0.58
     المعيارى
    0.57
     AssemblyCompany
    0.55
    Tôi
    0.55
     betweenstory
    0.53
    حياته
    0.52
    about
    0.52
     Tôi
    0.51
    Activations Density 0.001%

    No Known Activations