© 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. 11387
    Prev
    Next
    INDEX
    Explanations

    terms related to sparsity in data representation and reconstruction methodologies

    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
    UnsafeEnabled
    -0.81
     AssemblyVersion
    -0.79
    تقاوى
    -0.77
     Efq
    -0.75
    onames
    -0.73
     greateſt
    -0.73
     pleaſure
    -0.72
     الحره
    -0.71
     Majefty
    -0.69
     Diſ
    -0.67
    POSITIVE LOGITS
     spars
    0.58
    dillo
    0.52
    reveal
    0.50
    uland
    0.49
     bristles
    0.48
     schaffen
    0.46
    ido
    0.46
     Lasso
    0.46
    Files
    0.45
     onCreateView
    0.44
    Activations Density 0.035%

    No Known Activations