© 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. 1-CLT-HP
    7. 15018
    Prev
    Next
    INDEX
    Explanations

    back and forth, synagogue

    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
     Synagogue
    -1.36
     synagogue
    -1.29
     synag
    -1.04
    RectangleBorder
    -0.79
    UrlResolution
    -0.79
     fieldNum
    -0.78
    cshtml
    -0.78
     EconPapers
    -0.65
    MessageTagHelper
    -0.65
    NewUrlParser
    -0.63
    POSITIVE LOGITS
     universale
    0.59
     quæ
    0.58
     habet
    0.53
     Meksiku
    0.52
    Write
    0.50
     Sedgwick
    0.49
    ogues
    0.49
     Bowen
    0.47
     bogor
    0.47
    hæng
    0.47
    Activations Density 0.051%

    No Known Activations