© 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. 13981
    Prev
    Next
    INDEX
    Explanations

    references to rewards or rewarding situations

    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
     Suzy
    -0.81
    findpost
    -0.79
     Spie
    -0.75
    Odkazy
    -0.75
     tasche
    -0.72
     mcqueen
    -0.72
     Iain
    -0.71
     monks
    -0.68
     isolado
    -0.68
     Jha
    -0.68
    POSITIVE LOGITS
     Rewards
    1.23
     reward
    1.19
     rewards
    1.16
     Reward
    1.14
    Rewards
    1.12
    rewards
    1.04
    Reward
    1.00
    reward
    0.94
     rewarding
    0.81
     rewarded
    0.78
    Activations Density 0.003%

    No Known Activations