© 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. 43770
    Prev
    Next
    INDEX
    Explanations

    world

    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
    انيا
    -0.49
    temp
    -0.48
    andes
    -0.47
    mia
    -0.46
    pan
    -0.45
    v
    -0.45
    lias
    -0.44
        
    -0.44
    ti
    -0.44
    tom
    -0.44
    POSITIVE LOGITS
    StructEnd
    0.79
     архивлан
    0.77
     Efq
    0.69
     Monfieur
    0.68
     ostavi
    0.65
     $_"
    0.63
     ويكيميديا
    0.63
    Pratique
    0.61
     Theſe
    0.61
     getItemCount
    0.60
    Activations Density 0.148%

    No Known Activations