© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94577
    Prev
    Next
    INDEX
    Explanations

    ar

    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
     this
    -0.51
     the
    -0.50
     a
    -0.47
     inimes
    -0.40
    paddingBottom
    -0.40
    setLayoutManager
    -0.40
     one
    -0.39
     sitesinde
    -0.38
    ところ
    -0.38
     fometimes
    -0.38
    POSITIVE LOGITS
    ValueStyle
    0.88
    providedIn
    0.85
     المعيارى
    0.84
    DoubleQuotes
    0.83
     ویکی‌آمباردا
    0.77
     saites
    0.75
     Chwiliwch
    0.72
    abetes
    0.70
     BoxFit
    0.69
     <<<<<<<<<<<<<<
    0.66
    Activations Density 0.016%

    No Known Activations