© 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. 72537
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    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
    kháu
    -0.93
     Efq
    -0.81
     Савезне
    -0.80
     Theſe
    -0.78
     zelve
    -0.75
    setVerticalGroup
    -0.72
    новништво
    -0.71
     EClass
    -0.71
    Amicalement
    -0.69
    FieldBuilder
    -0.69
    POSITIVE LOGITS
     held
    0.56
    HtmlAttribute
    0.52
    ViewImports
    0.44
    GEBURTS
    0.44
     sur
    0.40
    MemoryWarning
    0.40
     ver
    0.39
     tempor
    0.38
    Import
    0.37
     master
    0.37
    Activations Density 0.002%

    No Known Activations