© 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. 20240
    Prev
    Next
    INDEX
    Explanations

    references to court cases or legal proceedings

    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
     JpaRepository
    -0.91
    findpost
    -0.83
    ValueGenerated
    -0.81
     GetEnumerator
    -0.80
     GenerationType
    -0.79
     مشين
    -0.77
    出版年
    -0.75
     viewDidLoad
    -0.72
    IUrlHelper
    -0.69
     MainAxisSize
    -0.69
    POSITIVE LOGITS
    팅
    0.40
     bombas
    0.40
     these
    0.40
     anzi
    0.39
     groundwork
    0.39
     anse
    0.38
     словами
    0.38
     Wurzel
    0.37
     synthesis
    0.37
     vitu
    0.37
    Activations Density 0.005%

    No Known Activations