© 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. 5-CLT-HP
    7. 93072
    Prev
    Next
    INDEX
    Explanations

    Numbers/Digits

    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
     moment
    -0.41
    分かります
    -0.38
    .
    -0.37
    stufen
    -0.36
     woman
    -0.36
    înt
    -0.36
    lost
    -0.35
    ian
    -0.35
    W
    -0.34
     bout
    -0.33
    POSITIVE LOGITS
     Roskov
    0.93
     دیکھیے
    0.82
     Мексичка
    0.81
    GraphicsUnit
    0.81
    ItemBackground
    0.81
    RegressionTest
    0.80
    MigrationBuilder
    0.79
    ///</
    0.79
    RegistryLite
    0.79
    oa̍t
    0.77
    Activations Density 0.003%

    No Known Activations