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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14300
    Prev
    Next
    INDEX
    Explanations

    political critique and references to economic issues

    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
    Not in Any Lists

    No Comments

    Negative Logits
    исленность
    -0.69
     OFDb
    -0.68
    thâu
    -0.63
    ποτε
    -0.63
    Демографія
    -0.62
     AppColors
    -0.59
     InputDecoration
    -0.57
    Domaine
    -0.57
    ULTURA
    -0.56
    BeginContext
    -0.56
    POSITIVE LOGITS
     very
    0.54
     okuyayım
    0.50
     insuffisamment
    0.50
     mucho
    0.49
     ویکی‌پدیای
    0.49
     molto
    0.48
    帖最后由
    0.48
    very
    0.48
     muito
    0.47
     fortemente
    0.47
    Activations Density 0.571%

    No Known Activations