© 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. 0-CLT-HP
    7. 42525
    Prev
    Next
    INDEX
    Explanations

    web pages and news reports

    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
     considering
    -0.70
    tivo
    -0.63
    vah
    -0.62
    ensis
    -0.60
    chini
    -0.60
    jah
    -0.60
    yen
    -0.59
     indicates
    -0.53
    zine
    -0.53
    inci
    -0.52
    POSITIVE LOGITS
    StoryboardSegue
    1.16
    LookAnd
    1.03
     resourceCulture
    0.98
    AccessorTable
    0.93
     disponibilités
    0.86
     '\\;'
    0.85
    WriteTagHelper
    0.81
    bootstrapcdn
    0.81
    RegistryLite
    0.81
    queryInterface
    0.80
    Activations Density 1.564%

    No Known Activations