© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4363
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     myſelf
    -0.73
     itſelf
    -0.73
     ſeveral
    -0.60
     whoſe
    -0.60
     faſt
    -0.56
     ReSharper
    -0.55
     ſta
    -0.55
     themſelves
    -0.54
     pleaſure
    -0.54
     Eſ
    -0.54
    POSITIVE LOGITS
    ########.
    0.79
    COUVER
    0.65
    OGND
    0.65
    AndroidJUnit
    0.63
    tagHelperRunner
    0.63
    webElementXpaths
    0.61
    EndGlobalSection
    0.59
    참고
    0.58
    IntoConstraints
    0.58
     AssemblyCompany
    0.57
    Activations Density 0.005%

    No Known Activations