© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1120
    Prev
    Next
    INDEX
    Explanations

    of

    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
     estimés
    -0.40
     experimento
    -0.39
     sorpresa
    -0.39
     mandatario
    -0.39
     экспери
    -0.38
    our
    -0.38
     लोग
    -0.38
    юрпри
    -0.37
     notre
    -0.37
     unseres
    -0.36
    POSITIVE LOGITS
    ISupport
    0.82
    IntoConstraints
    0.75
    expandindo
    0.69
     ویکی‌پدی
    0.68
    IVEREF
    0.66
    UnsafeEnabled
    0.66
    новниш
    0.65
    DebuggerStep
    0.64
     препратки
    0.62
     one
    0.61
    Activations Density 0.004%

    No Known Activations