© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9697
    Prev
    Next
    INDEX
    Explanations

    ries

    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
     iprot
    -0.64
     Rouse
    -0.56
     arbitrator
    -0.54
    verwijspagina
    -0.49
     wholesaler
    -0.49
     uș
    -0.49
     rancher
    -0.48
     BoxFit
    -0.47
    AnimationsModule
    -0.47
     hula
    -0.46
    POSITIVE LOGITS
    ंदीखरीदारी
    0.72
    DidLoad
    0.59
    Gilla
    0.58
    Enllaces
    0.57
    SpringBootTest
    0.56
     Roskov
    0.56
    تقاوى
    0.54
    vgili
    0.54
    }}</
    0.53
    MemoryWarning
    0.53
    Activations Density 0.027%

    No Known Activations