© 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. 12235
    Prev
    Next
    INDEX
    Explanations

    scenarios involving ethical dilemmas or moral questions

    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
     Monfieur
    -0.71
     Theſe
    -0.70
     myſelf
    -0.69
    Espèce
    -0.68
     Diſ
    -0.67
     purpoſe
    -0.66
     greateſt
    -0.66
     Beſ
    -0.65
     Sarm
    -0.65
     itſelf
    -0.65
    POSITIVE LOGITS
    adaptiveStyles
    0.62
     RouterModule
    0.54
    queryInterface
    0.51
     fair
    0.51
     Fair
    0.51
    oneofs
    0.48
    addContainerGap
    0.48
    ficulty
    0.47
     الحره
    0.47
    chê
    0.46
    Activations Density 0.071%

    No Known Activations