© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 21772
    Prev
    Next
    INDEX
    Explanations

    names of authors or contributors in academic works

    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
    <>();
    -0.48
    elemField
    -0.48
    complexContent
    -0.46
     iprot
    -0.45
     précédemment
    -0.44
     Harbour
    -0.44
     parlament
    -0.43
    ieniu
    -0.43
     parlamento
    -0.43
    delegate
    -0.42
    POSITIVE LOGITS
    ſelf
    0.76
     Houſe
    0.76
     pleaſure
    0.73
     Diſ
    0.72
     Reſ
    0.72
    ſelves
    0.71
     houſe
    0.71
    neſs
    0.68
     Վերցված
    0.67
     QtCore
    0.66
    Activations Density 0.036%

    No Known Activations