© 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. 1-CLT-HP
    7. 10928
    Prev
    Next
    INDEX
    Explanations

    highlight

    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
     Highlight
    -0.86
    Highlight
    -0.86
     highlight
    -0.85
     highlights
    -0.81
    highlight
    -0.77
    highlights
    -0.74
    <bos>
    -0.69
    Highlights
    -0.69
     Highlights
    -0.67
    highlighted
    -0.66
    POSITIVE LOGITS
    ViewFeatures
    0.61
     Numerade
    0.59
    jstor
    0.55
    WireFormatLite
    0.54
     Wicidata
    0.52
     /#
    0.50
     ExecuteAsync
    0.50
    tened
    0.49
    JRadioButton
    0.49
    risch
    0.49
    Activations Density 0.017%

    No Known Activations