© 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. 1-CLT-HP
    7. 14906
    Prev
    Next
    INDEX
    Explanations

    single

    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
    single
    -0.95
    Single
    -0.93
     Single
    -0.92
     single
    -0.91
    SINGLE
    -0.90
     SINGLE
    -0.83
     singles
    -0.68
     Singles
    -0.65
    シングル
    -0.60
     シングル
    -0.59
    POSITIVE LOGITS
     AssemblyCompany
    0.66
    CloseOperation
    0.52
    //</
    0.50
    jsxFileName
    0.49
    ellschaft
    0.48
     autorytatywna
    0.46
    Geplaatst
    0.46
     μην
    0.45
     ***!
    0.45
    omock
    0.45
    Activations Density 0.133%

    No Known Activations