© 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. 3241
    Prev
    Next
    INDEX
    Explanations

    acknowledge

    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
     of
    -0.44
     gants
    -0.41
    ged
    -0.39
     langues
    -0.38
     teken
    -0.37
     ausgeschlossen
    -0.36
     diarias
    -0.36
     halaman
    -0.36
    서는
    -0.35
     supérieur
    -0.35
    POSITIVE LOGITS
     CreateTagHelper
    0.90
    Jeografia
    0.81
    UrlResolution
    0.77
     ujednoznacz
    0.77
    +#+#
    0.75
    DockStyle
    0.75
     jsPsych
    0.75
    findpost
    0.73
    jbl
    0.70
    LLocation
    0.70
    Activations Density 0.002%

    No Known Activations