© 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. 5-CLT-HP
    7. 5124
    Prev
    Next
    INDEX
    Explanations

    but

    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
    PerformLayout
    -0.54
    #
    -0.46
     abor
    -0.40
     admit
    -0.39
     Spra
    -0.38
     Pry
    -0.37
    ัติ
    -0.37
    ArgumentParser
    -0.36
     Caramel
    -0.36
    ->___
    -0.36
    POSITIVE LOGITS
    tvguidetime
    0.67
    erráneo
    0.62
    ChildScrollView
    0.59
    CollectionUtils
    0.59
    verwijspagina
    0.59
     defStyle
    0.58
    EDEFAULT
    0.58
    хьтан
    0.57
    MockMvc
    0.57
    EntityFramework
    0.56
    Activations Density 0.001%

    No Known Activations