© 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. 4-CLT-HP
    7. 618
    Prev
    Next
    INDEX
    Explanations

    published/unpublished

    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
    TestBed
    -0.62
    ✨:
    -0.55
    SizeF
    -0.49
     pageContext
    -0.46
    цездатний
    -0.46
    InjectAttribute
    -0.46
     IconData
    -0.46
    قایناقلار
    -0.45
    ціє
    -0.45
    MENAFN
    -0.42
    POSITIVE LOGITS
     desist
    0.60
    +#+
    0.60
    ScopeManager
    0.59
    ⓧ
    0.59
    jspx
    0.57
    IUrlHelper
    0.57
     незавершена
    0.56
     Heads
    0.56
     heads
    0.55
    skrä
    0.54
    Activations Density 0.013%

    No Known Activations