© 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. 937
    Prev
    Next
    INDEX
    Explanations

    of

    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
     EconPapers
    -0.58
    IVOS
    -0.57
    age
    -0.55
     kaarangay
    -0.54
     Hodg
    -0.52
    ijas
    -0.51
    aged
    -0.51
    Trichloroethane
    -0.51
     Preferencias
    -0.50
    prüche
    -0.50
    POSITIVE LOGITS
    findpost
    0.66
    //
    0.60
    #
    0.55
     nonatomic
    0.55
    archiviato
    0.54
    enterian
    0.51
    ContentAsync
    0.50
    cesis
    0.50
    yntaxException
    0.50
    AntiForgeryToken
    0.49
    Activations Density 0.000%

    No Known Activations