© 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. 5-CLT-HP
    7. 92703
    Prev
    Next
    INDEX
    Explanations

    code/mathematical equations

    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
    styleType
    -0.66
    ברס
    -0.63
    клопе
    -0.63
    DebuggerStep
    -0.62
    bootstrapcdn
    -0.62
    ModelSerializer
    -0.57
     ThemeData
    -0.56
     resourceCulture
    -0.56
    ]--;
    -0.56
    BeginInit
    -0.55
    POSITIVE LOGITS
    WebElementEntity
    0.65
     Wiseman
    0.56
     defStyle
    0.56
     estekak
    0.54
     Mooney
    0.50
    lapsingToolbar
    0.50
    Numeric
    0.50
     umum
    0.49
    MockBean
    0.49
    存于互联网档案馆
    0.49
    Activations Density 0.000%

    No Known Activations