© 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. 0-CLT-HP
    7. 94759
    Prev
    Next
    INDEX
    Explanations

    estate

    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
     useAuth
    -0.49
     camp
    -0.48
    RunWith
    -0.48
    IUrlHelper
    -0.47
     /\.(
    -0.45
     оригіналу
    -0.45
    NamedQueries
    -0.44
     DOI
    -0.41
    }")]
    -0.41
     Camp
    -0.41
    POSITIVE LOGITS
    rungsseite
    1.18
    tagHelperRunner
    0.78
    цездатний
    0.77
    aarrggbb
    0.73
     مشين
    0.71
     Shakspeare
    0.71
    ChildScrollView
    0.69
     Exacts
    0.67
     وتسجيلات
    0.67
    TargetException
    0.65
    Activations Density 0.142%

    No Known Activations