© 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. 4-CLT-HP
    7. 868
    Prev
    Next
    INDEX
    Explanations

    code

    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
    expandindo
    -0.75
     Италијани
    -0.64
     المعيارى
    -0.61
    enumii
    -0.57
    يميديا
    -0.57
     Meksiku
    -0.57
    enumi
    -0.55
    évaluateur
    -0.53
    género
    -0.50
     }{@
    -0.50
    POSITIVE LOGITS
    ImageContext
    0.51
    ATIVA
    0.50
    Dul
    0.49
    pidou
    0.48
    fastjson
    0.48
    Cartesian
    0.48
    Hentet
    0.48
    Council
    0.48
     Iz
    0.47
     verific
    0.47
    Activations Density 0.002%

    No Known Activations