© 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. 42622
    Prev
    Next
    INDEX
    Explanations

    developed

    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
     developed
    -1.95
    developed
    -1.76
     Developed
    -1.49
    Developed
    -1.48
     desarrollado
    -1.34
     développé
    -1.27
     développ
    -1.26
     svilupp
    -1.09
     entwickelt
    -1.05
     desenvol
    -1.03
    POSITIVE LOGITS
     future
    0.53
    łod
    0.48
    ChromeDriver
    0.48
     metaphorical
    0.47
     inquiry
    0.47
     auxiliary
    0.46
     further
    0.46
     enquiry
    0.46
     email
    0.46
     recruitment
    0.45
    Activations Density 0.533%

    No Known Activations