© 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. 5-CLT-HP
    7. 97475
    Prev
    Next
    INDEX
    Explanations

    code

    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
    errHandler
    -0.66
    :✨
    -0.57
    StructEnd
    -0.56
    UnitTesting
    -0.52
     smallpox
    -0.52
    basicConfig
    -0.51
     resourceCulture
    -0.51
    Демографія
    -0.50
    مصادر
    -0.49
    سطس
    -0.48
    POSITIVE LOGITS
     <",
    0.63
    Aktualisiert
    0.62
    enumi
    0.56
    GroupLayout
    0.55
    ⃣
    0.54
    FontOfSize
    0.53
    esgue
    0.53
     BorderRadius
    0.53
     stand
    0.53
    even
    0.53
    Activations Density 0.037%

    No Known Activations