© 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. 91970
    Prev
    Next
    INDEX
    Explanations

    People/individuals

    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
    omock
    -0.60
     allAfrica
    -0.58
    codiles
    -0.55
     Leche
    -0.54
     Autorizaciones
    -0.53
    FontOfSize
    -0.52
    τερα
    -0.50
     isInitialized
    -0.50
     AssemblyCompany
    -0.49
    heds
    -0.49
    POSITIVE LOGITS
     or
    1.09
     или
    0.62
    astify
    0.54
    或
    0.53
    /
    0.53
     and
    0.52
    หรือ
    0.50
    -/
    0.50
     atau
    0.49
    Ҭ
    0.48
    Activations Density 0.000%

    No Known Activations