© 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. 96708
    Prev
    Next
    INDEX
    Explanations

    academic/scientific content

    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
    protoimpl
    -0.57
     stället
    -0.57
     plais
    -0.57
     prisonniers
    -0.55
     bäst
    -0.54
     sœurs
    -0.53
     assuré
    -0.52
     fédé
    -0.52
     selezione
    -0.52
    تقاوى
    -0.52
    POSITIVE LOGITS
    anyeol
    0.60
    auré
    0.59
    UTERS
    0.57
    ETTI
    0.57
    ellingham
    0.56
    itaine
    0.56
     etc
    0.56
    참고
    0.56
    ricula
    0.56
     Ike
    0.56
    Activations Density 0.036%

    No Known Activations