© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45970
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific abstracts

    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
    Autoritní
    -0.64
    AddWithValue
    -0.55
    kháu
    -0.54
     مرئيه
    -0.50
    forRoot
    -0.48
     bezeichneter
    -0.48
    новниш
    -0.47
    orkan
    -0.47
     Vitae
    -0.45
     médecins
    -0.45
    POSITIVE LOGITS
    complexContent
    0.82
    RefNanny
    0.65
    MessageTagHelper
    0.60
     IndexPath
    0.55
    kaya
    0.55
    braucher
    0.53
     BorderRadius
    0.52
    ItemBackground
    0.51
     Angele
    0.51
    transQ
    0.51
    Activations Density 0.029%

    No Known Activations