© 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. 20-CLT-HP
    7. 76458
    Prev
    Next
    INDEX
    Explanations

    Mixed data/code

    np_max-act-logits · 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
    AnimationsModule
    -0.39
    月号
    -0.39
    不服
    -0.39
    modb
    -0.37
    PageModule
    -0.37
     jScrollPane
    -0.37
    KommentareTeilen
    -0.36
    ENCY
    -0.36
     Initializes
    -0.36
    msgTypes
    -0.36
    POSITIVE LOGITS
     Roskov
    0.85
    Autoritní
    0.71
     autorytatywna
    0.65
     onOptions
    0.64
     viewDidLoad
    0.63
    WriteTagHelper
    0.62
    SpringBootTest
    0.60
    ineno
    0.60
     CreateTagHelper
    0.60
     onCreateView
    0.59
    Activations Density 0.000%

    No Known Activations