© 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. 0-CLT-HP
    7. 41869
    Prev
    Next
    INDEX
    Explanations

    Numbers and dollar signs

    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
    <bos>
    -0.92
     Theſe
    -0.71
    windowFixed
    -0.70
    AddTagHelper
    -0.68
    invokeLater
    -0.66
     ſeveral
    -0.64
    adaptiveStyles
    -0.61
     purpoſe
    -0.61
     whoſe
    -0.60
     Diſ
    -0.59
    POSITIVE LOGITS
     be
    0.88
     get
    0.75
     have
    0.74
     find
    0.69
     refer
    0.69
     assume
    0.63
     give
    0.63
     see
    0.61
     make
    0.60
     know
    0.60
    Activations Density 0.074%

    No Known Activations