© 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. 1-CLT-HP
    7. 9405
    Prev
    Next
    INDEX
    Explanations

    Asbury

    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
    脚注の使い方
    -0.66
    orski
    -0.63
    Portail
    -0.61
    ligently
    -0.61
    GEBURTSDATUM
    -0.60
    BeginContext
    -0.60
    RectangleBorder
    -0.60
     تضيفلها
    -0.58
    idemiology
    -0.57
    ValueGeneration
    -0.57
    POSITIVE LOGITS
     grecque
    0.54
     littéraire
    0.53
     régionale
    0.50
     literario
    0.48
    taca
    0.46
     consolidated
    0.46
     canadienne
    0.46
     consolidating
    0.45
     bosque
    0.45
     viaggio
    0.44
    Activations Density 0.094%

    No Known Activations