© 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. 10647
    Prev
    Next
    INDEX
    Explanations

    technical/medical documents

    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
    rafts
    -1.37
    raft
    -1.09
    angi
    -0.79
    RAFT
    -0.64
    rafted
    -0.56
    draft
    -0.55
     raft
    -0.54
     Raft
    -0.54
     rafts
    -0.53
    windowFixed
    -0.53
    POSITIVE LOGITS
    MessageTagHelper
    0.69
    CloseOperation
    0.57
    istoitu
    0.57
     utafitiHapana
    0.57
    ագրություններ
    0.56
     StatefulWidget
    0.56
    VersionUID
    0.55
    енча
    0.54
     bienvenue
    0.54
    ंदीखरीदारी
    0.54
    Activations Density 0.081%

    No Known Activations