© 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. 91808
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
     Jurí
    -0.55
    Попис
    -0.51
    FormBorderStyle
    -0.48
    }{*}{
    -0.48
    Typed
    -0.48
     yêu
    -0.47
    ENTAL
    -0.47
    はじめに
    -0.45
     fú
    -0.45
     hod
    -0.45
    POSITIVE LOGITS
    adaptiveStyles
    0.61
    RegressionTest
    0.58
    XmlEnum
    0.56
    ModelForm
    0.53
    engkapnya
    0.53
     JpaRepository
    0.53
    CopyWith
    0.52
    Espèce
    0.51
    subplots
    0.50
     könnte
    0.49
    Activations Density 0.005%

    No Known Activations