© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3800
    Prev
    Next
    INDEX
    Explanations

    experience

    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
    脚注の使い方
    -0.52
    TagHelper
    -0.51
    isand
    -0.48
     INCLUDE
    -0.46
     مواليد
    -0.46
     Offisielt
    -0.45
     success
    -0.45
    BeginContext
    -0.45
     الاطلاع
    -0.44
     Access
    -0.44
    POSITIVE LOGITS
     Italijani
    0.62
    Bakgrunnsstoff
    0.56
     Италијани
    0.56
    expandindo
    0.54
     تضيفلها
    0.52
     juges
    0.52
    ьаж
    0.52
     thereon
    0.50
     CallOverrides
    0.50
     Occidental
    0.49
    Activations Density 0.001%

    No Known Activations