© 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. 14457
    Prev
    Next
    INDEX
    Explanations

    phrases related to optimality or optimal choices

    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
     optimization
    -0.67
     onBind
    -0.66
     пера
    -0.64
     optimize
    -0.63
     optimizations
    -0.62
     Optimize
    -0.62
    NonNull
    -0.60
     Optimization
    -0.59
     helst
    -0.58
    tagext
    -0.57
    POSITIVE LOGITS
    letal
    0.88
    ragan
    0.85
     للمعارف
    0.84
    findpost
    0.82
     bst
    0.81
    ziert
    0.81
     ujednoznacz
    0.79
    脚注の使い方
    0.77
    Tikang
    0.76
    ItemBackground
    0.74
    Activations Density 0.006%

    No Known Activations