© 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. 112
    Prev
    Next
    INDEX
    Explanations

    as

    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
     sumpay
    -0.66
     entanto
    -0.66
    kháu
    -0.63
     */,
    -0.62
    InitVars
    -0.61
     versus
    -0.61
     vs
    -0.59
    стероид
    -0.57
     Мексичка
    -0.57
    сторі
    -0.57
    POSITIVE LOGITS
     do
    0.65
     soon
    0.60
    Datuak
    0.56
    ætter
    0.53
     does
    0.49
     CreateTagHelper
    0.49
    Soon
    0.48
    WebControls
    0.48
     you
    0.47
     réfugiés
    0.47
    Activations Density 0.001%

    No Known Activations