© 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. 15909
    Prev
    Next
    INDEX
    Explanations

    references to innocence or being portrayed as innocent

    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
     كومونز
    -0.79
     Dowling
    -0.71
     numberWith
    -0.60
     oração
    -0.59
     casket
    -0.59
     useDispatch
    -0.58
     externi
    -0.57
     Vib
    -0.57
     Vle
    -0.56
     Zwie
    -0.56
    POSITIVE LOGITS
     Innocence
    1.47
    innoc
    1.41
    Innoc
    1.40
     Innoc
    1.32
     Innocent
    1.30
     innocence
    1.25
    innocent
    1.25
     innocent
    1.23
     innoc
    1.15
     inocente
    1.06
    Activations Density 0.009%

    No Known Activations