© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 25820
    Prev
    Next
    INDEX
    Explanations

    terms related to media censorship and control

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     BoxDecoration
    -0.54
    ]};
    -0.53
     RequestMethod
    -0.52
    LabelTagHelper
    -0.52
    ConstraintMaker
    -0.52
     createSlice
    -0.50
    sscanf
    -0.49
    */),
    -0.48
    endphp
    -0.47
     Wiktionnaire
    -0.47
    POSITIVE LOGITS
     censorship
    1.05
     censura
    0.88
     Cens
    0.85
     censored
    0.84
     censor
    0.83
    ftagPool
    0.65
     censure
    0.64
    censored
    0.64
     controlled
    0.63
    审查
    0.62
    Activations Density 0.181%

    No Known Activations