© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10555
    Prev
    Next
    INDEX
    Explanations

    Australians

    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
     nakalista
    -1.07
     Australians
    -0.98
    antine
    -0.73
    
    -0.71
     Audiodateien
    -0.70
    Filmografie
    -0.69
     arşivlendi
    -0.66
     noDo
    -0.65
    nologue
    -0.65
    twimg
    -0.65
    POSITIVE LOGITS
    pani
    0.43
    σσ
    0.43
     duda
    0.39
    kod
    0.38
     grossen
    0.37
    x
    0.36
    SafeMath
    0.35
     دان
    0.35
    co
    0.35
    host
    0.35
    Activations Density 0.043%

    No Known Activations