© 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. 4400
    Prev
    Next
    INDEX
    Explanations

    groups of people

    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
    <bos>
    -0.59
     EconPapers
    -0.57
     AssemblyVersion
    -0.55
    Distribuzione
    -0.51
    ’
    -0.50
    twimg
    -0.49
    runApp
    -0.49
    ])):
    -0.48
    })),
    -0.47
    upyter
    -0.47
    POSITIVE LOGITS
    PageFactory
    0.69
     have
    0.66
     uſe
    0.65
     ſtand
    0.63
     ſch
    0.59
    FlatAppearance
    0.58
    ólicos
    0.57
     was
    0.56
    HtmlAttribute
    0.56
     lettore
    0.55
    Activations Density 0.001%

    No Known Activations