© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2667
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
    ReusableCell
    -0.61
    +#+#
    -0.57
    WebControls
    -0.54
    bootstrapcdn
    -0.51
    GRANTED
    -0.51
    ValueStyle
    -0.50
    PreferredItem
    -0.49
    uoti
    -0.48
    IsContent
    -0.47
    Concentr
    -0.46
    POSITIVE LOGITS
     Wiktionnaire
    0.70
     Baillargeon
    0.52
    yship
    0.51
     Toms
    0.50
     ekonomi
    0.49
     erreur
    0.48
    lccn
    0.48
     Ekonomi
    0.48
     infidelity
    0.48
     disambiguazione
    0.48
    Activations Density 0.003%

    No Known Activations