© 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. 20-CLT-HP
    7. 77684
    Prev
    Next
    INDEX
    Explanations

    z

    np_max-act-logits · 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
     kasarigan
    -0.76
    MessageTagHelper
    -0.62
    MessageOf
    -0.60
    Vidite
    -0.57
     Infórmanos
    -0.54
    #
    -0.54
    Rujuakan
    -0.53
     Administrativna
    -0.53
    /*
    -0.53
    ///</
    -0.53
    POSITIVE LOGITS
    RetentionPolicy
    0.63
    Vorlage
    0.53
    brero
    0.52
     gangen
    0.50
    SuppressWarnings
    0.49
    Honorable
    0.49
    jątk
    0.48
    FJ
    0.48
     spéciaux
    0.48
    Swag
    0.48
    Activations Density 0.006%

    No Known Activations