© 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. 21087
    Prev
    Next
    INDEX
    Explanations

    the possessive form of pronouns

    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
     their
    -0.85
    EDEFAULT
    -0.83
    medriver
    -0.80
     your
    -0.78
    tudiant
    -0.75
     own
    -0.73
    Their
    -0.72
    cirq
    -0.71
     THEIR
    -0.70
    ụp
    -0.70
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.63
    ergies
    0.59
    InSection
    0.58
    IndentedString
    0.55
     AssemblyProduct
    0.54
     Ader
    0.54
    Co
    0.53
    WithMany
    0.53
     BaseModel
    0.52
    elemField
    0.52
    Activations Density 0.075%

    No Known Activations