© 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. 1-CLT-HP
    7. 10022
    Prev
    Next
    INDEX
    Explanations

    names, emails, or locations

    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
     snippetHide
    -0.71
     CreateTagHelper
    -0.69
     AssemblyTitle
    -0.68
    awtextra
    -0.66
    DotNetBar
    -0.65
    IContainer
    -0.65
    XmlType
    -0.65
    IonicModule
    -0.63
    ArgsConstructor
    -0.63
    kháu
    -0.63
    POSITIVE LOGITS
    "}>
    0.51
    blockquote
    0.50
     mech
    0.47
    വാ
    0.47
     Moda
    0.47
     valet
    0.46
     mecha
    0.46
     epa
    0.46
     Observatory
    0.45
    Mech
    0.45
    Activations Density 0.021%

    No Known Activations