© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30901
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate ownership or relationships between objects

    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
    Negative Logits
     itſelf
    -1.30
     myſelf
    -1.17
     disambiguazione
    -1.05
     themſelves
    -1.02
     pleaſure
    -1.00
     himſelf
    -1.00
     poffible
    -0.96
    ſelf
    -0.95
     Majefty
    -0.93
     photolibrary
    -0.92
    POSITIVE LOGITS
     an
    0.77
     a
    0.75
     
    0.69
     as
    0.60
     more
    0.57
     at
    0.55
     two
    0.51
    </h3>
    0.51
     so
    0.50
    </h4>
    0.50
    Activations Density 0.070%

    No Known Activations