© 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. 93876
    Prev
    Next
    INDEX
    Explanations

    active

    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
     active
    -2.45
    active
    -2.00
    Active
    -1.92
     Active
    -1.80
     aktiven
    -1.60
     ACTIVE
    -1.58
    ACTIVE
    -1.56
     actif
    -1.52
     aktif
    -1.48
     activo
    -1.45
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.83
    +#+#
    0.78
     IBOutlet
    0.77
    izability
    0.71
     Cze
    0.69
    AndroidJUnit
    0.68
     Shakspeare
    0.68
     StatelessWidget
    0.68
     primitives
    0.68
     trypto
    0.67
    Activations Density 0.357%

    No Known Activations