© 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. 4-CLT-HP
    7. 2219
    Prev
    Next
    INDEX
    Explanations

    code/technical snippets

    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
     Reginald
    -0.71
     unknownFields
    -0.66
    awtextra
    -0.64
     >=",
    -0.61
     resized
    -0.60
    Portale
    -0.58
    Lähteet
    -0.58
     مشين
    -0.57
    ypep
    -0.57
    DropColumn
    -0.57
    POSITIVE LOGITS
     Moff
    0.47
     trainee
    0.40
     Dawson
    0.38
     المؤ
    0.38
     qualifier
    0.37
    roek
    0.37
     Patna
    0.37
     pewno
    0.37
     phenomenon
    0.37
     Preserve
    0.37
    Activations Density 0.003%

    No Known Activations