© 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. 18837
    Prev
    Next
    INDEX
    Explanations

    phrases and variations related to accusations

    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
    Negative Logits
     pien
    -0.68
     down
    -0.67
    PL
    -0.63
     flywheel
    -0.61
    ené
    -0.59
     Shir
    -0.59
    Jereo
    -0.59
    chium
    -0.57
    ọt
    -0.57
    Shir
    -0.56
    POSITIVE LOGITS
     accused
    1.27
     accuse
    1.25
     accuses
    1.19
     accusing
    1.16
    accus
    1.11
     accusation
    1.00
     accus
    0.99
     acusa
    0.97
     accusations
    0.96
    accu
    0.94
    Activations Density 0.004%

    No Known Activations