© 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. 29855
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to liability and court decisions

    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
     snippetHide
    -0.88
    IsContent
    -0.82
    ContentAsync
    -0.81
    WithIOException
    -0.80
    原始内容存档于
    -0.77
     disponibilités
    -0.77
     otomatig
    -0.77
    脚注の使い方
    -0.74
     Vikipedi
    -0.73
    createClass
    -0.72
    POSITIVE LOGITS
    }}$\\
    0.41
    too
    0.40
    }))
    0.40
     too
    0.38
    CompoundButton
    0.37
     тоже
    0.35
     shares
    0.35
    そも
    0.34
    ereich
    0.34
    ירה
    0.34
    Activations Density 0.025%

    No Known Activations