© 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. 5232
    Prev
    Next
    INDEX
    Explanations

    references to statistical or mathematical models

    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
     Kla
    -0.67
    ความ
    -0.64
    mailto
    -0.63
    Чу
    -0.60
    achten
    -0.59
     Susie
    -0.59
     gulp
    -0.58
     Gare
    -0.57
     grab
    -0.57
     зе
    -0.57
    POSITIVE LOGITS
     MODEL
    1.62
     Model
    1.49
     Models
    1.45
     models
    1.44
    MODEL
    1.44
    Models
    1.41
     MODELS
    1.35
     model
    1.34
    models
    1.31
    model
    1.30
    Activations Density 0.200%

    No Known Activations