© 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. 11618
    Prev
    Next
    INDEX
    Explanations

    references to accountability and advocacy for community issues

    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
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.66
    참고
    -0.54
    tagHelperRunner
    -0.53
    featureID
    -0.50
    multer
    -0.49
    TagMode
    -0.44
     (
    -0.44
    (?)
    -0.43
    setopt
    -0.43
     весьма
    -0.42
    POSITIVE LOGITS
     myſelf
    0.94
     pleaſure
    0.90
     itſelf
    0.88
     Monfieur
    0.80
     purpoſe
    0.79
     raiſ
    0.78
     faſt
    0.77
     ſtate
    0.75
     houſe
    0.75
     iſt
    0.74
    Activations Density 0.161%

    No Known Activations