© 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. 3529
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

    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
     autorytatywna
    -0.66
    canestro
    -0.57
     thiệu
    -0.57
     препратки
    -0.51
    ScopeManager
    -0.50
    enderror
    -0.49
    offsetof
    -0.48
    Pautan
    -0.48
     Atta
    -0.47
    verte
    -0.47
    POSITIVE LOGITS
    wpi
    0.52
    slidesPer
    0.52
    TintMode
    0.51
    脚注の使い方
    0.49
    ies
    0.48
    usermodel
    0.48
     nargin
    0.47
    <%=
    0.47
    Footnotes
    0.46
    IES
    0.44
    Activations Density 0.001%

    No Known Activations