© 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. 14055
    Prev
    Next
    INDEX
    Explanations

    Australian

    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
    altor
    -0.44
    oup
    -0.41
    czy
    -0.41
    ئو
    -0.40
     getNombre
    -0.40
     geht
    -0.40
    ť
    -0.40
     zug
    -0.39
     zugleich
    -0.39
     brazil
    -0.39
    POSITIVE LOGITS
     betweenstory
    0.69
    IUrlHelper
    0.66
    ftagPool
    0.66
     initComponents
    0.60
    eterangan
    0.59
    ьаж
    0.59
    parsedMessage
    0.59
    WireFormat
    0.59
    ParallelGroup
    0.58
    GHIJKLM
    0.58
    Activations Density 0.010%

    No Known Activations