© 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. 92794
    Prev
    Next
    INDEX
    Explanations

    part

    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
    .
    -0.52
     l
    -0.52
     la
    -0.48
     le
    -0.47
     (
    -0.46
     w
    -0.44
     
    -0.43
    ,
    -0.43
    <eos>
    -0.43
     `
    -0.43
    POSITIVE LOGITS
    出版年
    0.91
     Theſe
    0.82
     useAppContext
    0.80
     iconFacebook
    0.80
    AddTagHelper
    0.79
    Personensuche
    0.78
    вгений
    0.75
     itſelf
    0.75
     $_"
    0.74
    ſelf
    0.74
    Activations Density 0.064%

    No Known Activations