© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42086
    Prev
    Next
    INDEX
    Explanations

    stocks

    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
    AndEndTag
    -1.07
     vapours
    -1.05
     vapors
    -1.03
     gusts
    -0.98
    存于互联网档案馆
    -0.94
     AssemblyProduct
    -0.94
     vapour
    -0.94
    NameInMap
    -0.92
    MigrationBuilder
    -0.91
    ImageContext
    -0.90
    POSITIVE LOGITS
     of
    0.55
     stay
    0.48
     doigts
    0.41
     coming
    0.40
     чего
    0.39
     oreilles
    0.39
     akhir
    0.38
    træ
    0.37
     ortaya
    0.35
     live
    0.34
    Activations Density 0.167%

    No Known Activations