© 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. 23060
    Prev
    Next
    INDEX
    Explanations

    evaluative terms that denote extremes, such as 'best' and 'worst'

    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
    ulfon
    -0.59
    AnimationsModule
    -0.58
    лости
    -0.53
    httphttps
    -0.52
    serviceWorker
    -0.52
     deaf
    -0.50
    sí
    -0.49
     sí
    -0.48
     uuidv
    -0.48
    wps
    -0.47
    POSITIVE LOGITS
    الحياه
    0.72
     lenker
    0.69
     ***!
    0.66
    fromnode
    0.59
    SharedCtor
    0.59
    Бележки
    0.59
    núť
    0.59
     siquiera
    0.58
    limsy
    0.57
    قایناق‌لار
    0.56
    Activations Density 0.011%

    No Known Activations