© 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. 93858
    Prev
    Next
    INDEX
    Explanations

    recognition

    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
     ſmall
    -0.83
     leſs
    -0.79
     perſon
    -0.71
     purpoſe
    -0.71
     fubject
    -0.69
     ſch
    -0.67
     theſe
    -0.67
     houſe
    -0.66
     itſelf
    -0.65
     ſeveral
    -0.65
    POSITIVE LOGITS
    LookAnd
    0.66
    TagHelpers
    0.58
    usermodel
    0.57
    onAttach
    0.57
     AssemblyCompany
    0.54
    Rhestr
    0.54
    InjectAttribute
    0.54
    TemporalType
    0.53
     المعيارى
    0.53
    QMetaType
    0.52
    Activations Density 0.246%

    No Known Activations