© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1126
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or ownership of items and 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
     myſelf
    -1.09
     ainfi
    -1.05
     Monfieur
    -0.94
     Theſe
    -0.89
     ſtate
    -0.88
     feroit
    -0.86
     pauv
    -0.85
     becauſe
    -0.84
     zelve
    -0.84
     themſelves
    -0.82
    POSITIVE LOGITS
     had
    0.94
     tiene
    0.75
     
    0.74
     has
    0.74
     Had
    0.73
     punya
    0.73
     mempunyai
    0.72
    有一個
    0.72
     have
    0.71
     Has
    0.70
    Activations Density 0.836%

    No Known Activations