© 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. 0-CLT-HP
    7. 38238
    Prev
    Next
    INDEX
    Explanations

    boat

    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
     boat
    -0.68
     key
    -0.66
     II
    -0.65
     gun
    -0.63
     dog
    -0.61
     basic
    -0.46
     Spread
    -0.46
     ii
    -0.46
    : 
    -0.45
    hofen
    -0.43
    POSITIVE LOGITS
    contentLoaded
    0.85
     defaultstate
    0.84
    хьтан
    0.82
     Мексичка
    0.76
    cèse
    0.73
    клопе
    0.70
    RegistryLite
    0.69
     onOptions
    0.69
    ///</
    0.68
    HasMaxLength
    0.68
    Activations Density 0.066%

    No Known Activations