© 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. 5913
    Prev
    Next
    INDEX
    Explanations

    asked

    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
    theless
    -0.63
     Monfieur
    -0.56
    ſelf
    -0.55
    StoreMessageInfo
    -0.52
    EnableWeb
    -0.50
     cucchiai
    -0.50
     Majefty
    -0.49
     Conſ
    -0.48
    ſelves
    -0.48
     lives
    -0.47
    POSITIVE LOGITS
     me
    0.75
     us
    0.67
     most
    0.61
     виправивши
    0.58
     нами
    0.56
    ándonos
    0.53
     Team
    0.52
    ionato
    0.51
    majority
    0.50
     मुझे
    0.49
    Activations Density 0.001%

    No Known Activations