© 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. 0-CLT-HP
    4. 40954
    Prev
    Next
    INDEX
    Explanations

    Politics

    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
     Theſe
    -0.94
    liness
    -0.87
    存于互联网档案馆
    -0.87
     Monfieur
    -0.86
    theless
    -0.86
     neutrons
    -0.86
    poptosis
    -0.85
    ſelf
    -0.85
    sterious
    -0.84
     ―――――
    -0.84
    POSITIVE LOGITS
    s
    0.73
    WithIOException
    0.48
    Exc
    0.40
     cosa
    0.39
     te
    0.38
    Darn
    0.38
    supports
    0.36
     Land
    0.36
     bas
    0.35
    toArray
    0.35
    Activations Density 0.195%

    No Known Activations