© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4953
    Prev
    Next
    INDEX
    Explanations

    Quin

    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
     للاسماء
    -0.99
    hyrchwyd
    -0.79
     nakalista
    -0.63
    fjspx
    -0.62
    Hochspringen
    -0.61
    expandindo
    -0.60
    parsedMessage
    -0.59
     disponibilités
    -0.59
    principalColumn
    -0.59
    存于互联网档案馆
    -0.57
    POSITIVE LOGITS
    ädie
    0.55
    intellij
    0.48
     Market
    0.48
     frame
    0.47
     plane
    0.47
    IY
    0.47
     Sieben
    0.47
    navigationItem
    0.47
    YL
    0.46
     Journal
    0.46
    Activations Density 0.009%

    No Known Activations