© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14015
    Prev
    Next
    INDEX
    Explanations

    the

    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
     the
    -0.56
     csomag
    -0.53
     istimewa
    -0.52
     marad
    -0.49
     függ
    -0.48
     berbahaya
    -0.48
     communiquer
    -0.48
    czaj
    -0.46
     néz
    -0.46
    جانب
    -0.46
    POSITIVE LOGITS
    DockStyle
    1.03
    Personendaten
    1.02
     незавершена
    0.86
    styleType
    0.80
     itſelf
    0.79
    MigrationBuilder
    0.78
    SharedDtor
    0.77
    клопе
    0.72
    లాలు
    0.72
    ----</
    0.71
    Activations Density 0.008%

    No Known Activations