© 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. 72259
    Prev
    Next
    INDEX
    Explanations

    Destruction/Damage

    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
     Unbe
    -0.49
     Fault
    -0.46
     uved
    -0.42
    ніципалі
    -0.42
    Fault
    -0.42
    bable
    -0.41
    pening
    -0.41
     capables
    -0.40
     dommage
    -0.40
    URLException
    -0.40
    POSITIVE LOGITS
     dropped
    1.03
     destroyed
    1.01
     busted
    1.00
     washed
    0.99
     smashed
    0.98
     popped
    0.98
     blown
    0.97
     burned
    0.96
     collapsed
    0.95
     flooded
    0.94
    Activations Density 0.000%

    No Known Activations