© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92577
    Prev
    Next
    INDEX
    Explanations

    s

    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
    NamedQueries
    -0.51
    WindowConstants
    -0.50
     Replies
    -0.50
    GEBURTSDATUM
    -0.50
    cloudfront
    -0.50
     Cita
    -0.50
     Италијани
    -0.50
    MigrationBuilder
    -0.48
    SBATCH
    -0.48
    BASEPATH
    -0.48
    POSITIVE LOGITS
     what
    0.73
     whats
    0.66
     known
    0.65
     it
    0.63
    الإنجليزية
    0.62
     better
    0.61
     What
    0.60
     wrong
    0.60
     currently
    0.59
     right
    0.57
    Activations Density 0.015%

    No Known Activations