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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15389
    Prev
    Next
    INDEX
    Explanations

    rhetorical and propaganda language used to persuade or manipulate audiences

    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
    OGND
    -0.72
    Portály
    -0.62
    الحياه
    -0.60
     disambiguazione
    -0.59
    ########.
    -0.58
    ModelSerializer
    -0.57
    Portale
    -0.57
     goû
    -0.57
     Portail
    -0.57
    runApp
    -0.57
    POSITIVE LOGITS
     rhetoric
    2.25
     rhetor
    1.71
     rhetorical
    1.71
    rhe
    1.60
     Rhetoric
    1.59
     Rhetor
    1.43
     propaganda
    1.32
     speeches
    1.13
     keynote
    0.99
     eloquence
    0.98
    Activations Density 0.020%

    No Known Activations