© 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. 5165
    Prev
    Next
    INDEX
    Explanations

    strategic

    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
    tagHelperRunner
    -0.75
    ValueStyle
    -0.63
     يتيمه
    -0.60
     ArrayAdapter
    -0.59
    slidesPer
    -0.59
     useState
    -0.58
    useState
    -0.56
     censo
    -0.55
     GLFW
    -0.54
    mybatisplus
    -0.53
    POSITIVE LOGITS
     alignment
    0.62
     planning
    0.60
    stoke
    0.58
     direction
    0.58
    EDEFAULT
    0.57
    //</
    0.54
     priorities
    0.54
     formulation
    0.52
     sourcing
    0.52
    MessageOf
    0.52
    Activations Density 0.002%

    No Known Activations