© 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. 19874
    Prev
    Next
    INDEX
    Explanations

    terms related to indemnity and legal reimbursement

    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
    ombang
    -0.57
    жалуйста
    -0.56
    ungkinan
    -0.55
     Cowell
    -0.52
     leva
    -0.51
     Linz
    -0.51
    Activator
    -0.50
     option
    -0.50
    ruhe
    -0.50
    sweise
    -0.49
    POSITIVE LOGITS
     indemn
    0.98
     reimburse
    0.96
    DropColumn
    0.96
     reimbursement
    0.95
     reimbursed
    0.91
     indemnity
    0.90
     Indem
    0.85
     reimbur
    0.82
     doInBackground
    0.82
     Indemnity
    0.78
    Activations Density 0.003%

    No Known Activations