© 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. 20-CLT-HP
    7. 72048
    Prev
    Next
    INDEX
    Explanations

    Code and programming snippets

    np_max-act-logits · 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
     >=",
    -0.54
    lccn
    -0.53
     вікі
    -0.52
     unange
    -0.52
     esternos
    -0.52
     архивлан
    -0.48
    TintMode
    -0.48
    getMsg
    -0.47
    zerland
    -0.45
     Flask
    -0.44
    POSITIVE LOGITS
    InstanceState
    0.73
    XmlAccessorType
    0.72
     EconPapers
    0.71
     disambiguazione
    0.62
    حياته
    0.58
    initComponents
    0.56
    RetentionPolicy
    0.54
     REACT
    0.54
    PRWEB
    0.52
    hasMoreElements
    0.52
    Activations Density 0.000%

    No Known Activations