© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 46169
    Prev
    Next
    INDEX
    Explanations

    ethical

    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
    SpringBootTest
    -0.76
     InputDecoration
    -0.64
     المعيارى
    -0.61
     nahilalakip
    -0.60
    #
    -0.59
     تانيه
    -0.57
    localctx
    -0.57
     rentrée
    -0.56
     nación
    -0.55
    IVEREF
    -0.54
    POSITIVE LOGITS
    Abandon
    0.60
    jenost
    0.57
     Dormit
    0.56
     ecce
    0.56
     Abandon
    0.55
     Baillargeon
    0.53
     hacking
    0.53
     Dons
    0.52
     onlyOwner
    0.51
     Hacking
    0.51
    Activations Density 0.008%

    No Known Activations