© 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. 91708
    Prev
    Next
    INDEX
    Explanations

    dating sites

    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
     debout
    -0.54
     brancas
    -0.53
     frågan
    -0.50
     extérieurs
    -0.49
     hadapan
    -0.47
     sogno
    -0.47
     pintadas
    -0.46
     cérami
    -0.46
     vrais
    -0.45
     domanda
    -0.45
    POSITIVE LOGITS
     AssemblyCompany
    0.78
     propOrder
    0.73
    TagHelpers
    0.71
    Reprints
    0.67
     yolks
    0.63
    windowFixed
    0.63
    andoah
    0.63
    webElementXpaths
    0.61
     SUDOC
    0.61
     jPanel
    0.60
    Activations Density 0.002%

    No Known Activations