© 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. 12-RES-MATRYOSHKA-DC
    7. 5368
    Prev
    Next
    INDEX
    Explanations

    terms related to medical or health topics

    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
     <=",
    -0.59
    RegressionTest
    -0.57
    ########.
    -0.56
     mídia
    -0.56
    tikzpicture
    -0.54
     SafeMath
    -0.54
     condição
    -0.53
     dynamique
    -0.53
     lenker
    -0.49
     gavetas
    -0.47
    POSITIVE LOGITS
    NOPQRST
    0.71
     fishes
    0.54
    TemporalType
    0.52
    ोड़
    0.51
    rute
    0.51
    ̓
    0.50
     nhiêu
    0.49
     motorcycles
    0.49
     kick
    0.48
    permum
    0.47
    Activations Density 1.815%

    No Known Activations