© 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. 20407
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives indicating levels of health or wellbeing

    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
    </i>
    -0.73
    low
    -0.63
    </b>
    -0.62
     low
    -0.62
    kom
    -0.60
     Low
    -0.59
    high
    -0.58
    oman
    -0.57
     rendah
    -0.56
     useCallback
    -0.56
    POSITIVE LOGITS
    weile
    0.94
     correctes
    0.91
    wiſe
    0.91
     shewn
    0.90
     Efq
    0.86
    Оста
    0.85
    daß
    0.84
    ^(@)
    0.83
     myſelf
    0.83
     iſt
    0.83
    Activations Density 0.042%

    No Known Activations