© 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. 20900
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and implications of actions

    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
     Carlin
    -0.95
    enchymal
    -0.93
     Bader
    -0.92
     restTemplate
    -0.84
     Cowan
    -0.82
    🔥🔥
    -0.81
     Sis
    -0.80
     Wis
    -0.78
    ist
    -0.76
     Hodges
    -0.74
    POSITIVE LOGITS
    ing
    2.78
    ING
    2.05
    ة
    1.09
    ingi
    0.99
    ingan
    0.98
    ating
    0.94
    ingdon
    0.94
    izing
    0.94
    ingh
    0.93
    ingin
    0.91
    Activations Density 0.536%

    No Known Activations