© 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. 20-CLT-HP
    7. 71725
    Prev
    Next
    INDEX
    Explanations

    Syrian

    np_max-act-logits · 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
    tagHelperRunner
    -0.81
    featureID
    -0.77
     externi
    -0.67
     Reverso
    -0.65
     Italijanski
    -0.64
     town
    -0.62
    AddTagHelper
    -0.61
     AssemblyCompany
    -0.59
    клопе
    -0.59
     American
    -0.58
    POSITIVE LOGITS
    AnimationsModule
    0.49
     réguli
    0.48
    getahuan
    0.47
     StatelessWidget
    0.46
     användas
    0.46
     reír
    0.45
    globalData
    0.44
    /***/
    0.43
    rospy
    0.43
    memorial
    0.42
    Activations Density 0.000%

    No Known Activations