© 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. 1-CLT-HP
    7. 13587
    Prev
    Next
    INDEX
    Explanations

    instructions or tasks

    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
     المعيارى
    -0.82
    cipated
    -0.68
    ofern
    -0.65
    Grit
    -0.64
    PageContext
    -0.63
    %"),
    -0.61
     Swing
    -0.60
    *}{
    -0.60
    getRuntime
    -0.60
    '])->
    -0.58
    POSITIVE LOGITS
     propOrder
    0.49
    ádza
    0.45
     gynhyrchwyd
    0.44
     aikaa
    0.43
     ulang
    0.42
    envolvimento
    0.42
     Gefäng
    0.42
     ilma
    0.41
     revanche
    0.40
     siguran
    0.40
    Activations Density 0.002%

    No Known Activations