© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1142
    Prev
    Next
    INDEX
    Explanations

    nouns related to food and dining experiences

    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
     autorytatywna
    -1.09
    Jeografia
    -0.71
    ftagPool
    -0.69
     يتيمه
    -0.62
    TypedDataSet
    -0.62
    
    -0.62
    Personendaten
    -0.59
    leria
    -0.54
     snippetHide
    -0.53
     millions
    -0.52
    POSITIVE LOGITS
     errands
    0.75
     afternoon
    0.70
     evening
    0.69
     вечер
    0.65
     errand
    0.63
     morning
    0.62
    afternoon
    0.60
    evening
    0.59
    abstractmethod
    0.57
     dinner
    0.56
    Activations Density 1.104%

    No Known Activations