© 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. 5-CLT-HP
    7. 94911
    Prev
    Next
    INDEX
    Explanations

    IP

    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
    EndInit
    -0.84
    KURZBESCHREIBUNG
    -0.84
     @"/
    -0.71
    Gambas
    -0.71
    windowFixed
    -0.68
     المعيارى
    -0.68
    readystatechange
    -0.66
     typelib
    -0.66
    Bakgrunnsstoff
    -0.66
     kaarangay
    -0.65
    POSITIVE LOGITS
     ilgili
    0.41
    熟悉的
    0.38
     of
    0.38
    キロ
    0.38
    વી
    0.38
    migrationBuilder
    0.37
    が発生
    0.37
    v
    0.35
     presa
    0.35
     veux
    0.35
    Activations Density 0.001%

    No Known Activations