© 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. 5-CLT-HP
    7. 92234
    Prev
    Next
    INDEX
    Explanations

    names of people/places

    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
     intptr
    -0.45
    __':
    -0.44
     skala
    -0.42
    Compiled
    -0.42
    ajuato
    -0.41
     Soria
    -0.41
     Correspondent
    -0.41
    #
    -0.40
    __':
    -0.40
     penjual
    -0.40
    POSITIVE LOGITS
     betweenstory
    0.97
    SourceChecksum
    0.87
    BASEPATH
    0.82
    AddTagHelper
    0.76
    WebServlet
    0.68
    TagMode
    0.67
    +#+#
    0.66
    adaptiveStyles
    0.65
    ValueStyle
    0.62
     Winaray
    0.62
    Activations Density 0.003%

    No Known Activations