© 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. 24917
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or ownership

    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
    s
    -0.85
    zustellen
    -0.71
     is
    -0.70
    éos
    -0.69
     the
    -0.64
     Griffin
    -0.63
    ingles
    -0.63
    chts
    -0.62
    unas
    -0.62
     Nar
    -0.62
    POSITIVE LOGITS
     Rave
    0.85
     ModelExpression
    0.82
     myſelf
    0.80
     Houſe
    0.78
     Amadeus
    0.77
     ſtand
    0.76
     doInBackground
    0.75
     témoins
    0.75
     Lave
    0.74
    Hav
    0.73
    Activations Density 0.013%

    No Known Activations