© 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-RES-MATRYOSHKA-DC
    7. 13829
    Prev
    Next
    INDEX
    Explanations

    references to advocacy or lobbying efforts

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.75
    TagHelper
    -0.68
     transfieras
    -0.66
    \}.
    -0.66
     StringTokenizer
    -0.62
    ClientSize
    -0.61
     Administrativna
    -0.60
     Италијани
    -0.59
    SharedDtor
    -0.59
    URLException
    -0.59
    POSITIVE LOGITS
     advocacy
    2.16
     Advocacy
    1.93
     boast
    1.25
     boasted
    1.24
     boasting
    1.16
     boasts
    1.11
    Advoc
    1.05
     lobbying
    1.02
     bragging
    1.01
     brag
    0.98
    Activations Density 0.007%

    No Known Activations