© 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. 43704
    Prev
    Next
    INDEX
    Explanations

    railways

    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
     Efq
    -1.02
     myſelf
    -0.94
     iſt
    -0.86
     Monfieur
    -0.86
     itſelf
    -0.84
     ſever
    -0.83
     ainfi
    -0.83
    abestanden
    -0.81
     ſeveral
    -0.81
     ―――――
    -0.80
    POSITIVE LOGITS
    e
    0.98
    i
    0.94
    y
    0.84
    a
    0.72
    ‌ای
    0.66
    o
    0.58
    /
    0.54
    ing
    0.54
    ed
    0.53
     e
    0.53
    Activations Density 0.073%

    No Known Activations