© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40209
    Prev
    Next
    INDEX
    Explanations

    influence, force or authority

    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
     power
    -1.48
    power
    -1.08
     Power
    -1.05
    Power
    -0.97
     POWER
    -0.90
    POWER
    -0.75
     puissance
    -0.68
    パワー
    -0.60
     pow
    -0.59
     to
    -0.55
    POSITIVE LOGITS
     itſelf
    1.13
     виправивши
    1.13
     <>",
    1.12
    脚注の使い方
    1.10
     myſelf
    1.08
     дописавши
    1.05
     betweenstory
    1.05
    MessageTagHelper
    1.04
     Efq
    1.02
    ſelf
    1.02
    Activations Density 0.036%

    No Known Activations