© 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. 24506
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to victims and refugees in conflicts

    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
     itſelf
    -0.90
     pleaſure
    -0.90
     houſe
    -0.86
     Efq
    -0.86
     chofe
    -0.86
     ſeveral
    -0.84
     myſelf
    -0.83
     ſtate
    -0.81
     Majefty
    -0.81
     Monfieur
    -0.80
    POSITIVE LOGITS
     off
    0.52
    بوابة
    0.50
     "
    0.49
     di
    0.48
    exe
    0.47
     fully
    0.47
     Fla
    0.47
    shit
    0.45
     form
    0.44
     T
    0.44
    Activations Density 0.027%

    No Known Activations