© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40286
    Prev
    Next
    INDEX
    Explanations

    composition, properties

    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
     Institute
    -0.52
     a
    -0.50
    oa̍t
    -0.49
     post
    -0.47
     open
    -0.47
    TagHelper
    -0.46
    IBOutlet
    -0.46
     HttpStatusCode
    -0.45
     Sh
    -0.44
     Rep
    -0.44
    POSITIVE LOGITS
     EconPapers
    0.79
     titolata
    0.76
    contentLoaded
    0.69
     réuss
    0.69
     inconnu
    0.68
     aveug
    0.65
     cardiaque
    0.64
     falsos
    0.63
     milioane
    0.62
    Tikang
    0.62
    Activations Density 0.064%

    No Known Activations