© 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. 23204
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements related to health

    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
    randrange
    -0.53
     LoggerFactory
    -0.49
    alignSelf
    -0.47
    EDEFAULT
    -0.46
    енча
    -0.44
     defStyleAttr
    -0.43
    的一次
    -0.43
    trum
    -0.42
    gatsby
    -0.41
     tục
    -0.41
    POSITIVE LOGITS
     autorytatywna
    0.82
    ]$}
    0.79
    findpost
    0.76
    RenderAtEndOf
    0.72
     مرئيه
    0.69
    Autoritní
    0.69
    Hozzáférés
    0.68
     disambiguazione
    0.67
    jspx
    0.67
    Искәрмәләр
    0.65
    Activations Density 0.045%

    No Known Activations