© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4876
    Prev
    Next
    INDEX
    Explanations

    to

    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
     find
    -0.76
     simulate
    -0.75
     communicate
    -0.74
     provide
    -0.73
     introduce
    -0.73
     contribute
    -0.71
     generate
    -0.70
     receive
    -0.70
     deliver
    -0.69
     achieve
    -0.69
    POSITIVE LOGITS
     ſmall
    0.67
    بوابة
    0.67
     the
    0.63
     sqlSession
    0.63
     different
    0.63
     useAuth
    0.62
    viewDidLoad
    0.61
     each
    0.61
     this
    0.59
     humans
    0.58
    Activations Density 0.005%

    No Known Activations