© 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. 2411
    Prev
    Next
    INDEX
    Explanations

    with

    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
    Geplaatst
    -0.70
    stateMutability
    -0.59
     here
    -0.59
     hereof
    -0.58
    now
    -0.54
     THESIS
    -0.52
    here
    -0.52
     herein
    -0.51
     hereto
    -0.51
    stdafx
    -0.50
    POSITIVE LOGITS
    MENAFN
    0.56
    таратура
    0.52
    CloseOperation
    0.51
     AssemblyTitle
    0.51
     respond
    0.50
    awaiter
    0.50
     responding
    0.50
    
    0.49
    ValueGeneration
    0.49
     Expos
    0.48
    Activations Density 0.003%

    No Known Activations