© 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. 2930
    Prev
    Next
    INDEX
    Explanations

    Numbers and quantities

    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
    DebuggerNonUser
    -0.77
    matchCondition
    -0.70
    
    -0.69
    Vidite
    -0.69
     kasarigan
    -0.63
     endforeach
    -0.61
    EndInit
    -0.61
    ArgsConstructor
    -0.60
    BeginInit
    -0.60
     pinulongan
    -0.60
    POSITIVE LOGITS
     officers
    0.62
    Officers
    0.59
     yourselves
    0.59
     engineers
    0.58
     Officers
    0.54
    cientes
    0.51
    officers
    0.50
     oks
    0.50
    masters
    0.49
    ters
    0.48
    Activations Density 0.017%

    No Known Activations