© 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. 5-CLT-HP
    7. 2648
    Prev
    Next
    INDEX
    Explanations

    Organizations and locations

    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
    Personendaten
    -1.23
     kaarangay
    -1.18
    MigrationBuilder
    -1.11
     Roskov
    -1.11
     للاسماء
    -1.03
     beginnetje
    -1.01
    parsedMessage
    -1.00
    EndInit
    -0.99
     AssemblyCulture
    -0.97
    IUrlHelper
    -0.97
    POSITIVE LOGITS
    diteur
    0.36
    pp
    0.33
    photo
    0.30
    1
    0.29
    p
    0.29
     
    0.28
     p
    0.28
     pensa
    0.27
    l
    0.27
    2
    0.27
    Activations Density 0.790%

    No Known Activations