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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 5747
    Prev
    Next
    INDEX
    Explanations

    terms associated with nutrition and health-related concepts

    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
    batore
    -0.59
    contentLoaded
    -0.58
     Paglinawan
    -0.51
     onPostExecute
    -0.50
     aVar
    -0.50
    Lähteet
    -0.47
    atamente
    -0.46
    مصادر
    -0.45
     متعلقه
    -0.43
     tyle
    -0.43
    POSITIVE LOGITS
     qualquer
    0.77
     either
    0.75
     quelconque
    0.74
     anywhere
    0.73
     whichever
    0.73
    sizeCache
    0.72
     any
    0.71
     apapun
    0.71
    either
    0.70
     anybody
    0.70
    Activations Density 0.590%

    No Known Activations