© 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. 91579
    Prev
    Next
    INDEX
    Explanations

    articles/pronouns

    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
    WEBPACK
    -0.72
    ResumeLayout
    -0.67
    فحة
    -0.61
    CppMethod
    -0.61
    حوالہ
    -0.58
     vicenda
    -0.56
    .*")]
    -0.55
    ]")]
    -0.55
    قایناقلار
    -0.54
    setBold
    -0.54
    POSITIVE LOGITS
     intention
    1.04
     intent
    0.86
     intentions
    0.77
    intention
    0.75
     decision
    0.69
    intent
    0.66
     interest
    0.59
     intención
    0.59
     decisions
    0.57
     candidacy
    0.57
    Activations Density 0.006%

    No Known Activations