© 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. 0-CLT-HP
    7. 90882
    Prev
    Next
    INDEX
    Explanations

    deli

    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
    aarrggbb
    -0.68
    ized
    -0.63
    expandindo
    -0.59
    AndEndTag
    -0.57
    ele
    -0.56
     fund
    -0.54
    الحياه
    -0.54
     CreateTagHelper
    -0.52
     AspNetCore
    -0.51
    izr
    -0.50
    POSITIVE LOGITS
     erreurs
    0.60
    vants
    0.57
     vectorielle
    0.57
     visuales
    0.55
     vendidos
    0.54
     inscrição
    0.54
     illustrazione
    0.53
     participação
    0.53
     tiroirs
    0.53
    lative
    0.52
    Activations Density 0.125%

    No Known Activations