© 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. 0-CLT-HP
    7. 43424
    Prev
    Next
    INDEX
    Explanations

    useful

    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
     nổ
    -0.45
    bukaan
    -0.44
     teljes
    -0.43
     terci
    -0.42
     attacco
    -0.40
     rêves
    -0.40
     manto
    -0.40
    ensaft
    -0.40
     vœux
    -0.39
     prêtres
    -0.39
    POSITIVE LOGITS
     فريبيس
    1.13
    AddTagHelper
    1.03
     مشين
    0.83
    tagHelperRunner
    0.82
     Exacts
    0.81
    MemoryWarning
    0.80
    protoimpl
    0.77
    сылкі
    0.75
    bootstrapcdn
    0.75
    ResumeLayout
    0.73
    Activations Density 0.085%

    No Known Activations