© 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. 5131
    Prev
    Next
    INDEX
    Explanations

    information related to data analysis and quantification

    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
     trans
    -0.52
     sé
    -0.45
    <eos>
    -0.44
     concent
    -0.43
     
    -0.43
    ince
    -0.43
     “
    -0.42
    lect
    -0.41
     men
    -0.41
     gritos
    -0.41
    POSITIVE LOGITS
     kasarigan
    1.22
    setVerticalGroup
    1.12
    AnchorStyles
    1.11
     propOrder
    1.10
     Roskov
    1.05
    DockStyle
    1.03
    сылкі
    1.02
    MLLoader
    1.01
    بوابة
    0.96
    Искәрмәләр
    0.96
    Activations Density 0.089%

    No Known Activations