© 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. 32256
    Prev
    Next
    INDEX
    Explanations

    references to "GR" as a specific term or metric related to a context, likely involving analysis or statistics

    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
    InvalidProtocol
    -1.02
    μιουργ
    -1.00
    NoSuchAlgorithm
    -0.93
    aarrggbb
    -0.83
     CommonModule
    -0.82
     Meksiku
    -0.81
    Кры
    -0.81
    شهاد
    -0.79
     propOrder
    -0.78
    etheless
    -0.78
    POSITIVE LOGITS
     GR
    1.41
     gri
    1.21
     Gri
    1.16
    GR
    1.15
    gri
    0.99
    Gri
    0.99
     Griffin
    0.96
     gr
    0.83
     Griff
    0.83
    gr
    0.82
    Activations Density 0.026%

    No Known Activations