© 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. 512
    Prev
    Next
    INDEX
    Explanations

    Commonwealth

    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
    InvalidProtocol
    -0.69
    forKey
    -0.55
     AssemblyVersion
    -0.54
    arrête
    -0.52
     initComponents
    -0.52
    jspx
    -0.51
    __(/*!
    -0.49
     дописавши
    -0.48
    wpi
    -0.48
    مم
    -0.47
    POSITIVE LOGITS
     INE
    0.54
    stalgia
    0.51
     Abor
    0.50
    indigo
    0.50
    出版年
    0.49
     كورة
    0.49
    ionali
    0.49
    tedrale
    0.49
    xido
    0.48
    esgue
    0.48
    Activations Density 0.000%

    No Known Activations