© 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. 98197
    Prev
    Next
    INDEX
    Explanations

    Sports

    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
     externally
    -0.60
     externe
    -0.50
     internally
    -0.47
     universitaria
    -0.47
     répondu
    -0.47
    "=>"
    -0.45
     outside
    -0.45
    lias
    -0.44
    曖昧さ回避
    -0.44
    klä
    -0.44
    POSITIVE LOGITS
    sizeCache
    0.70
    GEBURTSDATUM
    0.62
    RTCF
    0.61
    Vidite
    0.60
    /*
    0.59
    siębior
    0.58
    ThroughAttribute
    0.58
    PKCS
    0.57
    protoc
    0.56
     LCCN
    0.56
    Activations Density 0.001%

    No Known Activations