© 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. 77693
    Prev
    Next
    INDEX
    Explanations

    social

    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
     surla
    -0.79
    Демографія
    -0.73
    richTextPanel
    -0.72
     EconPapers
    -0.71
    LookAnd
    -0.70
     snippetHide
    -0.69
     Jir
    -0.68
     JpaRepository
    -0.67
    Diweddarwch
    -0.66
    fjspx
    -0.66
    POSITIVE LOGITS
     ModelExpression
    0.55
     sociaux
    0.38
     médi
    0.37
    createCanvas
    0.36
     ExecuteAsync
    0.35
     vectorielle
    0.34
     trä
    0.34
     sosial
    0.33
     onCreateView
    0.32
     medias
    0.31
    Activations Density 0.002%

    No Known Activations