© 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. 5-CLT-HP
    7. 4047
    Prev
    Next
    INDEX
    Explanations

    political leaders

    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
    Filler
    -0.63
    Ecotoxicity
    -0.55
     utafitiHapana
    -0.53
    ilik
    -0.52
    ilang
    -0.52
    choline
    -0.52
    omyia
    -0.51
     Balloons
    -0.50
     Abroad
    -0.49
     FLIGHT
    -0.49
    POSITIVE LOGITS
    CloseOperation
    0.53
    TagMode
    0.50
    TabIndex
    0.48
    Trev
    0.43
    itemize
    0.43
    InputBorder
    0.43
    Dearest
    0.43
    :"-"`
    0.43
    ɵ
    0.41
    rxjs
    0.40
    Activations Density 0.001%

    No Known Activations