© 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. 91685
    Prev
    Next
    INDEX
    Explanations

    so

    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
    djangoproject
    -0.69
    IUrlHelper
    -0.63
     Мексичка
    -0.62
    Personendaten
    -0.57
    !*\
    -0.57
     SwitchCompat
    -0.56
    تقاوى
    -0.55
     AssemblyTitle
    -0.55
     ویکی‌پدی
    -0.54
    titleMargin
    -0.54
    POSITIVE LOGITS
    المشاركات
    0.59
     حالا
    0.53
    ließlich
    0.53
     stål
    0.51
    OTO
    0.49
    counting
    0.48
    WithFormat
    0.47
    mockMvc
    0.47
    reszcie
    0.47
    thaler
    0.46
    Activations Density 0.003%

    No Known Activations