© 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. 90886
    Prev
    Next
    INDEX
    Explanations

    magic and representation

    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
     miracle
    -1.16
     represented
    -1.15
     magic
    -0.96
    magical
    -0.95
    miracle
    -0.95
     magical
    -0.93
    magic
    -0.87
     miracles
    -0.85
    Magic
    -0.83
     Magic
    -0.79
    POSITIVE LOGITS
    ksz
    0.55
    getAttributes
    0.53
    jl
    0.50
    vill
    0.50
    ixels
    0.50
    antan
    0.49
     INSTR
    0.49
     Benth
    0.47
     prestazioni
    0.47
    agd
    0.46
    Activations Density 0.030%

    No Known Activations