© 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. 5045
    Prev
    Next
    INDEX
    Explanations

    ethics or programming code

    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
    InjectAttribute
    -0.55
    )++;
    -0.53
    
    -0.52
    feest
    -0.50
     ujednoznacz
    -0.49
    nosaurus
    -0.48
    WindowConstants
    -0.47
     surla
    -0.47
     חיצוניים
    -0.46
     actionTypes
    -0.46
    POSITIVE LOGITS
     hackers
    0.70
     Hacking
    0.62
    الحياه
    0.61
     hacker
    0.61
     hacking
    0.60
     Hacker
    0.59
    hacker
    0.58
    Weakness
    0.57
    Hacker
    0.54
    BufferException
    0.51
    Activations Density 0.000%

    No Known Activations