© 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. 16868
    Prev
    Next
    INDEX
    Explanations

    negative connotations associated with the term "bad."

    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
     Loom
    -0.91
    WireFormatLite
    -0.90
    Sucesor
    -0.84
    parsedMessage
    -0.78
     Crook
    -0.77
     onCreateView
    -0.77
    databind
    -0.77
    complexContent
    -0.76
     Lyra
    -0.76
    Referencie
    -0.75
    POSITIVE LOGITS
     BAD
    1.11
     Bad
    1.09
    Bad
    1.05
    BAD
    1.02
     bad
    0.98
    bad
    0.98
     worse
    0.84
     badly
    0.82
     worst
    0.74
    Worse
    0.72
    Activations Density 0.014%

    No Known Activations