© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 94010
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    ClientSize
    -0.52
    onViewCreated
    -0.51
    統領
    -0.49
    unger
    -0.48
    CodeAttribute
    -0.47
     prétend
    -0.47
     Minder
    -0.45
    wide
    -0.45
    bei
    -0.43
    bajo
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    0.65
    sess
    0.60
    spoken
    0.58
    sof
    0.57
    WebVitals
    0.57
    soft
    0.56
     يتيمه
    0.56
    service
    0.56
     Efq
    0.56
     Mens
    0.55
    Activations Density 0.002%

    No Known Activations