© 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. 43249
    Prev
    Next
    INDEX
    Explanations

    benchmark

    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
     Mistake
    -0.57
     mistake
    -0.56
     Cater
    -0.56
     cradle
    -0.53
     subsp
    -0.52
    ząd
    -0.50
     fancied
    -0.50
    SerializeField
    -0.50
     Automobiles
    -0.50
     Computers
    -0.50
    POSITIVE LOGITS
    évaluateur
    0.70
    hand
    0.59
    ftagPool
    0.59
    enterOuterAlt
    0.58
    Дереккөздер
    0.57
    Risultati
    0.56
     Infórmanos
    0.55
     Référence
    0.54
    MessageTagHelper
    0.54
    ThroughAttribute
    0.54
    Activations Density 0.077%

    No Known Activations