© 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. 5-CLT-HP
    7. 4670
    Prev
    Next
    INDEX
    Explanations

    economics

    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
    GOTREF
    -0.65
     bambina
    -0.52
     @"/
    -0.49
     attiva
    -0.49
    kada
    -0.49
     dipende
    -0.49
    Dug
    -0.49
    нрави
    -0.48
    djangoproject
    -0.48
     defaultstate
    -0.48
    POSITIVE LOGITS
     Intelligence
    0.76
    KommentareTeilen
    0.65
    Intelligence
    0.64
     FontWeight
    0.58
    InvalidProtocol
    0.57
    getRuntime
    0.54
     INTELL
    0.54
     ControllerBase
    0.52
    ništvo
    0.51
    intelligence
    0.50
    Activations Density 0.001%

    No Known Activations