© 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. 13358
    Prev
    Next
    INDEX
    Explanations

    students

    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
     OFDb
    -0.54
     môn
    -0.50
     crossover
    -0.49
    mael
    -0.49
    ()]);
    -0.48
    alberto
    -0.47
    ioso
    -0.47
    maid
    -0.47
    UnitId
    -0.46
     "/",
    -0.46
    POSITIVE LOGITS
     JADX
    0.65
    ſelf
    0.62
     UITableViewCell
    0.61
     يتيمه
    0.59
     myſelf
    0.58
     Anſ
    0.58
     Reſ
    0.56
     himſelf
    0.56
    NUMX
    0.55
    
    0.55
    Activations Density 0.006%

    No Known Activations