© 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. 14822
    Prev
    Next
    INDEX
    Explanations

    Comparison and anatomy

    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
    лтемелер
    -0.69
     INTERESAR
    -0.68
    Soorten
    -0.67
     AssemblyProduct
    -0.66
    はじめに
    -0.65
    зулта
    -0.65
     resourceCulture
    -0.65
    تقاوى
    -0.62
    ⋙
    -0.59
    soort
    -0.59
    POSITIVE LOGITS
    ly
    0.57
    ViewFeatures
    0.56
     ExecuteAsync
    0.54
    עה
    0.51
     Godt
    0.46
    ization
    0.42
    ally
    0.41
     MainAxisSize
    0.40
    tably
    0.40
    detectChanges
    0.40
    Activations Density 0.085%

    No Known Activations