© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 697
    Prev
    Next
    INDEX
    Explanations

    hunter

    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
     hunter
    -1.03
    hunter
    -0.87
    Hunter
    -0.84
     Hunter
    -0.82
     hunters
    -0.80
     HUNTER
    -0.79
     Hunters
    -0.77
    hunters
    -0.73
    :✨
    -0.69
     maîtres
    -0.58
    POSITIVE LOGITS
    GHIJKLM
    0.70
    __":
    
    0.68
     AssemblyCulture
    0.68
    *)((
    0.68
    __":
    0.65
    __':
    
    0.63
     صوتيه
    0.58
     vulgares
    0.57
     PublicKey
    0.55
     AssemblyProduct
    0.54
    Activations Density 0.020%

    No Known Activations