© 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. 77120
    Prev
    Next
    INDEX
    Explanations

    daw

    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
    ValueStyle
    -0.80
    setViewportView
    -0.71
    AndEndTag
    -0.60
    argout
    -0.59
    ContentAsync
    -0.57
     متعلقه
    -0.56
    TagHelpers
    -0.56
     चीज़ों
    -0.55
    čilo
    -0.55
     Chwiliwch
    -0.55
    POSITIVE LOGITS
     kelapa
    0.50
    w
    0.49
    alpa
    0.48
    zack
    0.48
     Falk
    0.48
     w
    0.43
     AssemblyCompany
    0.43
     Mot
    0.43
    roblast
    0.43
     Rot
    0.42
    Activations Density 0.002%

    No Known Activations