© 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. 18885
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives related to physical attributes and conditions

    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
    VIAF
    -0.88
    featureID
    -0.85
     Waray
    -0.82
    parsedMessage
    -0.75
     Roskov
    -0.70
     CreateTagHelper
    -0.70
     <",
    -0.69
    WriteAttribute
    -0.69
     doInBackground
    -0.67
     GenerationType
    -0.66
    POSITIVE LOGITS
     recent
    0.56
    orithmic
    0.52
    ness
    0.46
     intest
    0.46
    ginous
    0.45
     especially
    0.44
     critical
    0.44
    4
    0.44
    ro
    0.43
     particularly
    0.43
    Activations Density 0.003%

    No Known Activations