© 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. 4-CLT-HP
    7. 363
    Prev
    Next
    INDEX
    Explanations

    biographies

    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
     totalSupply
    -0.54
     незавершена
    -0.54
     pavillon
    -0.50
    msgTypes
    -0.49
     BoxFit
    -0.48
    følgelig
    -0.48
    vellous
    -0.47
    hasMoreElements
    -0.46
     magique
    -0.46
    AnchorStyles
    -0.46
    POSITIVE LOGITS
     שוליים
    0.52
     February
    0.52
     December
    0.51
     October
    0.51
     June
    0.50
     Citron
    0.50
    헌
    0.50
    Hochspringen
    0.49
    Parcelize
    0.49
     January
    0.49
    Activations Density 0.053%

    No Known Activations