© 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. 11407
    Prev
    Next
    INDEX
    Explanations

    HTML tags and their attributes

    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
    
    -1.09
    parsedMessage
    -1.05
     GenerationType
    -1.03
    sidemargin
    -0.94
    yntaxException
    -0.92
     виправивши
    -0.91
    ReusableCell
    -0.88
    تقاوى
    -0.88
     насељу
    -0.84
     Obrador
    -0.82
    POSITIVE LOGITS
     conten
    0.44
     re
    0.43
    .
    0.43
     and
    0.41
     are
    0.41
     alde
    0.40
     
    0.39
     segu
    0.38
     applied
    0.38
    頃は
    0.37
    Activations Density 0.003%

    No Known Activations