© 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. 455
    Prev
    Next
    INDEX
    Explanations

    economies

    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
    ToBounds
    -0.61
     Jefus
    -0.56
    potranspiration
    -0.54
    ConstraintMaker
    -0.50
    WriteTagHelper
    -0.50
    klere
    -0.50
    Rüyada
    -0.50
     Krakowie
    -0.48
    Sagittarius
    -0.48
     endblock
    -0.47
    POSITIVE LOGITS
     of
    0.65
    accueil
    0.56
    cended
    0.56
     entire
    0.55
     TextAppearance
    0.54
    ashian
    0.52
    StringCopy
    0.51
     esternos
    0.50
     whole
    0.49
    harmed
    0.48
    Activations Density 0.000%

    No Known Activations