© 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. 1-CLT-HP
    7. 14371
    Prev
    Next
    INDEX
    Explanations

    physical strength/weakness

    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
     rien
    -0.50
    sizeCache
    -0.49
     trebui
    -0.45
    ناية
    -0.42
     réve
    -0.42
    verifyException
    -0.41
    EndGlobalSection
    -0.40
    diyesi
    -0.39
     rekening
    -0.38
     menyem
    -0.38
    POSITIVE LOGITS
     Jefus
    0.87
     Thebes
    0.85
     Theſe
    0.84
     Majefty
    0.80
     Monfieur
    0.77
     Eſ
    0.71
     Efq
    0.70
     EconPapers
    0.69
     faſt
    0.68
     myſelf
    0.68
    Activations Density 0.067%

    No Known Activations