© 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. 73205
    Prev
    Next
    INDEX
    Explanations

    think

    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
    expandindo
    -0.68
    NameInMap
    -0.57
    AddTagHelper
    -0.57
    rrggbb
    -0.54
    UnsafeEnabled
    -0.53
     EClass
    -0.53
     Escribe
    -0.52
     disambiguazione
    -0.50
    parsedMessage
    -0.50
    Previews
    -0.49
    POSITIVE LOGITS
    下载附件
    0.66
     would
    0.64
     you
    0.59
     they
    0.57
     it
    0.57
     /\.
    0.56
     we
    0.51
     springfox
    0.50
     that
    0.50
     is
    0.50
    Activations Density 0.003%

    No Known Activations