© 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. 336
    Prev
    Next
    INDEX
    Explanations

    phrases or structures that describe examples or clarifications

    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
     purpoſe
    -0.77
     ſub
    -0.67
     Juifs
    -0.63
     ſen
    -0.61
     Diſ
    -0.61
     ſmall
    -0.61
     greateſt
    -0.61
     houſe
    -0.60
     Anſ
    -0.59
    "]);
    
    -0.58
    POSITIVE LOGITS
     например
    1.01
    例えば
    1.01
     like
    0.99
     bijvoorbeeld
    0.98
     např
    0.96
    比如
    0.95
    voorbeeld
    0.94
    like
    0.93
     beispielsweise
    0.93
    たとえば
    0.93
    Activations Density 0.923%

    No Known Activations