© 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. 41705
    Prev
    Next
    INDEX
    Explanations

    policy

    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
     policy
    -1.52
    policy
    -1.30
     POLICY
    -1.07
     Policy
    -1.04
    Policy
    -1.00
    POLICY
    -0.83
    政策
    -0.79
    strom
    -0.75
    politik
    -0.75
     policies
    -0.67
    POSITIVE LOGITS
    NewUrlParser
    0.62
    sequelize
    0.61
     ExecuteAsync
    0.59
    BASEPATH
    0.54
     ModelExpression
    0.52
    TypedDataSet
    0.52
     Batista
    0.52
    psia
    0.50
     Principe
    0.49
     indices
    0.49
    Activations Density 0.837%

    No Known Activations