© 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. 15755
    Prev
    Next
    INDEX
    Explanations

    the word related to censorship or content moderation

    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
     كره
    -0.59
     Avan
    -0.54
    Avan
    -0.52
    %");
    -0.50
    Crm
    -0.50
    kannt
    -0.49
    SqlDataReader
    -0.49
     Roskov
    -0.48
     useAuth
    -0.48
    actionMode
    -0.48
    POSITIVE LOGITS
     censorship
    3.66
     censor
    3.08
     Cens
    2.84
     censored
    2.69
     censura
    2.27
    cens
    2.09
    censored
    1.62
     cens
    1.46
     censure
    1.19
    ensors
    1.11
    Activations Density 0.001%

    No Known Activations