© 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. 4-CLT-HP
    7. 4668
    Prev
    Next
    INDEX
    Explanations

    the

    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
     autorytatywna
    -0.77
    eleste
    -0.57
     useRouter
    -0.55
    ederos
    -0.54
    RTHOOK
    -0.52
     graag
    -0.52
    :✨
    -0.51
    +#+#
    -0.51
     surla
    -0.50
    ⓧ
    -0.50
    POSITIVE LOGITS
    DockStyle
    0.63
     hObject
    0.54
     InputDecoration
    0.52
    TestingModule
    0.51
     BoxDecoration
    0.50
     estimated
    0.49
    GIH
    0.48
    atrième
    0.47
    onav
    0.47
    EClass
    0.47
    Activations Density 0.009%

    No Known Activations