© 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. 3449
    Prev
    Next
    INDEX
    Explanations

    caution

    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
    MigrationBuilder
    -0.70
     CreateTagHelper
    -0.68
     CITES
    -0.59
     utafitiHapana
    -0.58
    WindowConstants
    -0.56
    kuuta
    -0.56
    wahati
    -0.56
    SBATCH
    -0.56
    PreferredItem
    -0.55
    BagConstraints
    -0.55
    POSITIVE LOGITS
     leaving
    0.57
     getting
    0.56
     visiting
    0.56
     raising
    0.56
     using
    0.55
     taking
    0.54
     making
    0.53
     doing
    0.52
    using
    0.50
     staying
    0.50
    Activations Density 0.000%

    No Known Activations