© 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. 15886
    Prev
    Next
    INDEX
    Explanations

    pronouns indicating self-reference or addressing others

    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
    Autoritní
    -0.94
    RegressionTest
    -0.87
    Personendaten
    -0.82
    addCriterion
    -0.79
     Roskov
    -0.75
     TextAppearance
    -0.75
     Вікі
    -0.70
     createContext
    -0.70
     Paglinawan
    -0.68
    PerformLayout
    -0.65
    POSITIVE LOGITS
     should
    0.65
     mustn
    0.65
     need
    0.61
     ought
    0.58
    CloseOperation
    0.58
     Deber
    0.58
     shouldn
    0.57
     Should
    0.57
     SHOULD
    0.57
    should
    0.56
    Activations Density 0.176%

    No Known Activations