© 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. 5-CLT-HP
    7. 5009
    Prev
    Next
    INDEX
    Explanations

    submit

    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
     enví
    -0.52
     becauſe
    -0.49
    RenderAtEndOf
    -0.48
     Flü
    -0.47
    CloseOperation
    -0.45
    opsida
    -0.45
     decorativo
    -0.44
     nele
    -0.43
     Mindy
    -0.43
     Jefus
    -0.42
    POSITIVE LOGITS
     estimés
    0.64
    yntaxException
    0.54
    Diweddarwch
    0.52
    execSQL
    0.52
    etcode
    0.51
    rawDesc
    0.50
     سكانية
    0.50
     Elec
    0.50
    fusc
    0.50
    Chham
    0.50
    Activations Density 0.000%

    No Known Activations