© 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. 4823
    Prev
    Next
    INDEX
    Explanations

    Extracted article/blog snippets

    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
    SourceChecksum
    -0.93
    verwijspagina
    -0.66
    #
    -0.63
     дописавши
    -0.60
    EndInit
    -0.57
    Tikang
    -0.57
     Chwiliwch
    -0.56
    IsMutable
    -0.56
     wireType
    -0.56
    IUrlHelper
    -0.54
    POSITIVE LOGITS
     sauvages
    0.58
     CITIES
    0.58
    meteries
    0.57
    TEA
    0.56
    deutschland
    0.56
    مصادر
    0.56
    dead
    0.55
    Riot
    0.54
    — 
    0.54
    vereins
    0.54
    Activations Density 0.023%

    No Known Activations