© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 93552
    Prev
    Next
    INDEX
    Explanations

    Errors/Problems/Failures

    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
    )");
    
    -0.68
    %</
    -0.60
    "])
    
    -0.59
    }}</
    -0.59
    ++
    
    -0.58
    '))
    
    -0.58
     disponibilités
    -0.57
    "));
    
    -0.57
    "))
    
    -0.56
    ']))
    
    -0.56
    POSITIVE LOGITS
     surla
    0.69
    Lähteet
    0.67
    RemoveField
    0.63
     Italijani
    0.55
    awtextra
    0.54
    Referencie
    0.54
    Билгалдахарш
    0.53
    AddField
    0.50
    CodedInputStream
    0.50
     Reverso
    0.49
    Activations Density 0.003%

    No Known Activations