© 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. 5-CLT-HP
    7. 93508
    Prev
    Next
    INDEX
    Explanations

    Lists and enumerations

    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
     Vikipedi
    -0.58
    UpdateCommand
    -0.56
    IUrlHelper
    -0.54
    TableAdapter
    -0.53
    bitField
    -0.53
    بوس
    -0.53
    ProgressHUD
    -0.52
    urlpatterns
    -0.52
    Portail
    -0.52
    titleMargin
    -0.51
    POSITIVE LOGITS
    +#+
    0.54
    исленность
    0.52
     surla
    0.46
    новништво
    0.45
     massively
    0.44
     specifically
    0.44
    IANGLES
    0.43
     things
    0.42
     SqlDbType
    0.42
     exact
    0.41
    Activations Density 0.001%

    No Known Activations