© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90746
    Prev
    Next
    INDEX
    Explanations

    nis

    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
    nis
    -1.03
     are
    -0.80
    are
    -0.70
    is
    -0.52
    Are
    -0.49
     estn
    -0.45
     Are
    -0.43
     ARE
    -0.42
     piden
    -0.42
    šk
    -0.41
    POSITIVE LOGITS
    SharedCtor
    0.94
    المناصب
    0.91
    ArrowToggle
    0.88
     configureStore
    0.85
     ―――――
    0.80
    ImageContext
    0.80
     محفوظة
    0.79
     ModelExpression
    0.78
     Roskov
    0.78
     estekak
    0.76
    Activations Density 0.222%

    No Known Activations