© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 2019
    Prev
    Next
    INDEX
    Explanations

    categorization

    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
     categorical
    -0.62
     Categor
    -0.62
    Categor
    -0.47
     Romney
    -0.47
    categorical
    -0.45
    s
    -0.43
     papan
    -0.41
    end
    -0.41
    mí
    -0.41
    CEP
    -0.40
    POSITIVE LOGITS
     propOrder
    1.22
    Portale
    0.97
    theless
    0.85
     Efq
    0.85
    Cyfeiriadau
    0.83
     resourceCulture
    0.81
    μως
    0.81
    findpost
    0.81
     Exacts
    0.79
    protoimpl
    0.79
    Activations Density 0.506%

    No Known Activations