© 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. 32098
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of being alive or revived

    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
     AspNetCore
    -0.90
    CONSIN
    -0.85
     Myles
    -0.74
     Iain
    -0.66
    featureID
    -0.66
     cheese
    -0.65
    ers
    -0.62
     inappro
    -0.62
     Donegal
    -0.61
     Cheese
    -0.60
    POSITIVE LOGITS
     Alive
    1.52
     ALIVE
    1.37
    Alive
    1.36
     alive
    1.35
     revive
    1.30
    alive
    1.28
     revived
    1.09
     reviving
    1.06
     Vitality
    1.06
     revival
    0.96
    Activations Density 0.013%

    No Known Activations