© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93033
    Prev
    Next
    INDEX
    Explanations

    heart, chest

    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
     ब्रेकडाउन
    -0.71
     فريبيس
    -0.63
    mặt
    -0.62
     createState
    -0.61
     rendus
    -0.57
    rungsseite
    -0.56
    FormTagHelper
    -0.56
    anniversaire
    -0.56
    จึง
    -0.55
    apatalk
    -0.54
    POSITIVE LOGITS
     morbidity
    0.63
    RunAsync
    0.57
     oxidative
    0.50
     abnormalities
    0.50
     comorbidities
    0.50
     excitations
    0.50
     myocardial
    0.50
     homogeneity
    0.50
     thoracic
    0.49
     anisotropy
    0.49
    Activations Density 0.390%

    No Known Activations