© 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. 2726
    Prev
    Next
    INDEX
    Explanations

    import

    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
     saites
    -0.73
    SpringBootTest
    -0.65
    Viited
    -0.59
     HasFactory
    -0.59
     ffilmiau
    -0.54
    Bakgrunnsstoff
    -0.54
    ibald
    -0.53
    uterte
    -0.53
    UnsafeEnabled
    -0.52
    ubernur
    -0.52
    POSITIVE LOGITS
    })*/
    0.57
    ódó
    0.55
    NamedQueries
    0.54
     Tartar
    0.54
    ')));
    0.51
     Défense
    0.51
    (')
    0.51
    queryInterface
    0.50
     conseguenze
    0.50
     Prise
    0.49
    Activations Density 0.023%

    No Known Activations