© 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. 9930
    Prev
    Next
    INDEX
    Explanations

    references to self-directed actions or self-awareness

    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
     self
    -0.79
     Self
    -0.69
     SELF
    -0.63
    Self
    -0.61
     itself
    -0.57
    self
    -0.55
     Selbst
    -0.53
     zelf
    -0.51
    Selbst
    -0.50
    riwal
    -0.47
    POSITIVE LOGITS
     doInBackground
    0.88
     }}"></
    0.84
    ,‎
    0.79
     ویکی‌پدیای
    0.75
    ']?>
    0.73
    Collegamenti
    0.72
    )}</
    0.72
    endphp
    0.71
    مزید
    0.71
    })()
    0.70
    Activations Density 0.011%

    No Known Activations