© 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. 1-CLT-HP
    7. 10821
    Prev
    Next
    INDEX
    Explanations

    address

    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
    SharedDtor
    -0.95
    AddTagHelper
    -0.94
    IUrlHelper
    -0.88
    webElementXpaths
    -0.85
     nakalista
    -0.85
    GEBURTSDATUM
    -0.81
     address
    -0.79
    Address
    -0.79
    awtextra
    -0.79
     Address
    -0.75
    POSITIVE LOGITS
     Psico
    0.42
     Alcal
    0.39
     compositeur
    0.38
    nosti
    0.38
     Psicología
    0.36
     клю
    0.35
    PhysRevLett
    0.35
    spli
    0.35
     espon
    0.35
    sizeof
    0.35
    Activations Density 0.036%

    No Known Activations