© 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. 4-CLT-HP
    4. 2577
    Prev
    Next
    INDEX
    Explanations

    to/for

    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
     riuscito
    -0.59
     slaap
    -0.57
    rassing
    -0.54
     étoit
    -0.53
     duquel
    -0.50
     étoient
    -0.49
    ğum
    -0.49
     avoient
    -0.48
    verwijspagina
    -0.48
     conséquent
    -0.47
    POSITIVE LOGITS
    
    0.78
    قایناق‌لار
    0.66
     fit
    0.65
    sizeCache
    0.63
    NewUrlParser
    0.63
    elemField
    0.63
    webElement
    0.62
     ExecuteAsync
    0.61
    TestBed
    0.59
    pertory
    0.58
    Activations Density 0.007%

    No Known Activations