© 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. 9369
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and methodologies related to experiments

    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
    /**
    -0.80
     Cok
    -0.75
     кӀ
    -0.72
     Nicho
    -0.71
     Cody
    -0.69
     Kog
    -0.67
    etz
    -0.65
    ieza
    -0.65
     kaka
    -0.65
     mets
    -0.64
    POSITIVE LOGITS
     Villanueva
    0.68
     PAND
    0.66
    pandora
    0.66
     Fahren
    0.65
     Vidal
    0.64
     Josephus
    0.64
    setViewName
    0.64
     Paren
    0.63
     Peres
    0.63
     Horas
    0.63
    Activations Density 0.068%

    No Known Activations