© 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. 16366
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "edition."

    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
     Graves
    -0.78
    Graves
    -0.72
    over
    -0.66
    ev
    -0.65
    ra
    -0.64
     a
    -0.64
     ev
    -0.62
     ‘
    -0.62
     '
    -0.61
    al
    -0.59
    POSITIVE LOGITS
    Edition
    1.49
     Edition
    1.45
     edition
    1.42
    edition
    1.41
     editions
    1.34
     EDITION
    1.30
     Editions
    1.14
    __':
    
    1.13
    __":
    
    1.09
     Theſe
    1.07
    Activations Density 0.004%

    No Known Activations