© 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. 20-CLT-HP
    7. 77315
    Prev
    Next
    INDEX
    Explanations

    women's sports

    np_max-act-logits · 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
    بوابة
    -0.66
     Incre
    -0.62
     Sixty
    -0.60
     Critical
    -0.60
    Three
    -0.60
     Into
    -0.60
     Very
    -0.59
    To
    -0.59
    Subview
    -0.59
     Sensitive
    -0.59
    POSITIVE LOGITS
    prow
    0.43
     roulant
    0.42
     vérit
    0.42
     ainfi
    0.40
     AppCompat
    0.38
    hooter
    0.37
    ocats
    0.37
    FundMe
    0.36
    struzioni
    0.36
    〗
    0.36
    Activations Density 0.001%

    No Known Activations