© 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. 17787
    Prev
    Next
    INDEX
    Explanations

    discussions around moral implications and judgments in conflict contexts

    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
     vnder
    -0.62
    WireFormatLite
    -0.55
     extranjera
    -0.51
    Биография
    -0.49
    digkeit
    -0.49
     ]}
    -0.48
    Specificity
    -0.48
     ""],
    -0.48
    ایای
    -0.47
     negras
    -0.47
    POSITIVE LOGITS
     entanto
    1.05
     however
    1.02
    however
    0.84
     però
    0.80
    However
    0.76
    卻
    0.75
     tuttavia
    0.73
     However
    0.72
     όμως
    0.72
    etheless
    0.70
    Activations Density 0.263%

    No Known Activations