© 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. 6046
    Prev
    Next
    INDEX
    Explanations

    expressions of skepticism or disbelief about claims or statements

    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
    Datuak
    -0.61
    peł
    -0.58
    setopt
    -0.57
     CanadaChoose
    -0.54
    IBOutlet
    -0.54
    évaluateur
    -0.54
    RectangleBorder
    -0.53
     ext
    -0.53
    ValueStyle
    -0.52
     Normdatei
    -0.51
    POSITIVE LOGITS
     falsas
    0.58
     humaines
    0.57
     wholly
    0.55
     assolutamente
    0.55
     completely
    0.52
     misplaced
    0.52
     wrong
    0.52
     fallacy
    0.52
    false
    0.51
     mistaken
    0.51
    Activations Density 0.633%

    No Known Activations