© 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. 94598
    Prev
    Next
    INDEX
    Explanations

    ray

    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
     domestic
    -0.73
     ray
    -0.72
    enterOuterAlt
    -0.68
     للمعارف
    -0.68
     Ray
    -0.61
    tagHelperRunner
    -0.59
    CppCodeGen
    -0.59
     يتيمه
    -0.57
    ω
    -0.56
    own
    -0.56
    POSITIVE LOGITS
    sho
    0.63
    ship
    0.62
    sab
    0.60
    s
    0.59
    shower
    0.59
    safe
    0.57
    esine
    0.55
    science
    0.53
    shares
    0.53
     الرياضيه
    0.52
    Activations Density 0.091%

    No Known Activations