© 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. 71852
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    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
     to
    -0.80
     GenerationType
    -0.73
     unknownFields
    -0.71
     disambiguazione
    -0.65
    RenderAtEndOf
    -0.65
    енча
    -0.63
    IonicModule
    -0.63
    TestingModule
    -0.63
     hObject
    -0.61
    Jereo
    -0.60
    POSITIVE LOGITS
     can
    0.71
     could
    0.62
     will
    0.54
    setVerticalGroup
    0.47
     should
    0.47
     did
    0.45
     cán
    0.45
     COULD
    0.44
    could
    0.43
    бар
    0.41
    Activations Density 0.001%

    No Known Activations