© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11655
    Prev
    Next
    INDEX
    Explanations

    cla

    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
    contentLoaded
    -0.72
    Rhestr
    -0.71
    ValueStyle
    -0.68
     ModelExpression
    -0.68
     Italijanski
    -0.66
    thâu
    -0.61
     jScrollPane
    -0.60
     Bioaccumulative
    -0.57
     BoxFit
    -0.57
    出版年
    -0.57
    POSITIVE LOGITS
    s
    0.59
    gha
    0.53
    łop
    0.49
    smo
    0.49
    dly
    0.48
    sit
    0.48
    CppMethod
    0.47
    médi
    0.47
    dul
    0.46
    sis
    0.46
    Activations Density 0.035%

    No Known Activations