© 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. 0-CLT-HP
    7. 95115
    Prev
    Next
    INDEX
    Explanations

    court rulings and countdowns

    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
    gan
    -0.59
     progression
    -0.53
     disposition
    -0.52
    ness
    -0.48
     dispositions
    -0.48
     progre
    -0.47
     progressive
    -0.47
    s
    -0.46
     Progression
    -0.45
     mouvements
    -0.44
    POSITIVE LOGITS
    Hochspringen
    0.81
     الحره
    0.78
     GenerationType
    0.77
    Autoritní
    0.76
    enterOuterAlt
    0.73
    herself
    0.72
    daß
    0.72
    queryInterface
    0.71
    SequentialGroup
    0.69
    himself
    0.68
    Activations Density 0.243%

    No Known Activations