© 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. 10506
    Prev
    Next
    INDEX
    Explanations

    references to documentaries and their descriptions or content

    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
     propOrder
    -0.85
    bootstrapcdn
    -0.59
    زب
    -0.58
     Spelling
    -0.56
    ADELPHIA
    -0.56
    prüche
    -0.55
    Schule
    -0.55
     Turku
    -0.55
     Lese
    -0.54
     Bade
    -0.54
    POSITIVE LOGITS
     documentary
    1.11
     Documentary
    1.10
     documentaries
    1.08
    Documentary
    1.04
     documentaire
    0.93
     documental
    0.88
     footage
    0.64
    GenerationType
    0.63
    setVerticalGroup
    0.60
    Documented
    0.59
    Activations Density 0.038%

    No Known Activations