© 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. 4-CLT-HP
    7. 3170
    Prev
    Next
    INDEX
    Explanations

    lectures/talks

    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
    řské
    -0.62
    -------------</
    -0.61
    CrossRef
    -0.59
    $")
    -0.58
     /\.(
    -0.58
    ]--;
    -0.56
    AnchorStyles
    -0.56
    Bioaccumulative
    -0.55
    EDEFAULT
    -0.55
     cref
    -0.53
    POSITIVE LOGITS
     StatefulWidget
    0.56
    “
    0.50
    AddHtmlAttribute
    0.50
    contentLoaded
    0.50
    riwal
    0.46
    uesia
    0.46
     sento
    0.45
    Examine
    0.45
    IConfiguration
    0.45
     on
    0.43
    Activations Density 0.006%

    No Known Activations