© 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. 4-CLT-HP
    7. 358
    Prev
    Next
    INDEX
    Explanations

    em

    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
    IBarButtonItem
    -0.59
    cipital
    -0.56
    :✨
    -0.54
    hamshire
    -0.49
     couvre
    -0.48
    aternion
    -0.48
    RUnlock
    -0.48
     Famili
    -0.48
     cozinha
    -0.48
     ricetta
    -0.48
    POSITIVE LOGITS
    ThroughAttribute
    0.60
    tagHelperRunner
    0.55
    UnsafeEnabled
    0.53
     "..\..\
    0.49
    complexContent
    0.48
    ynos
    0.45
    barra
    0.44
     propOrder
    0.44
    💼
    0.43
     comp
    0.43
    Activations Density 0.002%

    No Known Activations