© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 459
    Prev
    Next
    INDEX
    Explanations

    arches/curves

    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
     AspNetCore
    -0.43
    ezers
    -0.40
     claim
    -0.39
    suf
    -0.39
     himo
    -0.39
    žek
    -0.38
    térature
    -0.38
    ereal
    -0.37
    assertNot
    -0.37
     Cone
    -0.36
    POSITIVE LOGITS
    InputBorder
    0.79
     BoxDecoration
    0.73
    存于互联网档案馆
    0.71
     fermés
    0.66
    WriteTagHelper
    0.65
     @"/
    0.65
     MessageBoxIcon
    0.61
    antd
    0.60
    LayoutConstraint
    0.59
    AccessorTable
    0.58
    Activations Density 0.002%

    No Known Activations