© 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. 12026
    Prev
    Next
    INDEX
    Explanations

    Named entities or technical terms

    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
     destructor
    -0.71
     Beatty
    -0.65
    CloseOperation
    -0.63
     reducer
    -0.59
    adox
    -0.58
     cuticle
    -0.54
     Cartier
    -0.54
    TestingModule
    -0.52
     Schmitt
    -0.52
     Oud
    -0.52
    POSITIVE LOGITS
     EconPapers
    0.80
     betweenstory
    0.64
    ChildScrollView
    0.53
    EndGlobalSection
    0.52
    はじめに
    0.52
     Zacks
    0.50
    řeba
    0.50
    Parental
    0.50
     vPvB
    0.49
    eful
    0.48
    Activations Density 0.012%

    No Known Activations