© 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. 0-CLT-HP
    7. 43172
    Prev
    Next
    INDEX
    Explanations

    regulate

    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
     vectorielles
    -1.14
     anún
    -1.12
     يتيمه
    -1.09
     larmes
    -1.07
     stället
    -1.06
     supérieurs
    -1.05
     igång
    -1.05
     disparu
    -1.05
     متعلقه
    -1.04
     financières
    -1.02
    POSITIVE LOGITS
     the
    2.13
     a
    1.65
     an
    1.45
     their
    1.33
     its
    1.20
     this
    1.20
     some
    1.20
     them
    1.14
     it
    1.13
     your
    1.13
    Activations Density 0.751%

    No Known Activations