© 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. 13930
    Prev
    Next
    INDEX
    Explanations

    rare/unusual words

    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
     kaarangay
    -0.66
     snag
    -0.63
    hira
    -0.60
    Namara
    -0.59
    kháu
    -0.56
     pinning
    -0.56
     Mancha
    -0.56
    CodedInputStream
    -0.54
    luence
    -0.52
     Putnam
    -0.51
    POSITIVE LOGITS
    orteur
    0.56
    argout
    0.54
    談社
    0.50
     Omen
    0.49
    avu
    0.48
     imagin
    0.47
    SessionFactory
    0.47
    s
    0.47
     Italijani
    0.47
     orizz
    0.46
    Activations Density 0.025%

    No Known Activations