© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 2213
    Prev
    Next
    INDEX
    Explanations

    concepts related to new developments or changes in evidence and data structures

    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
    Rhestr
    -0.59
    Toponymie
    -0.58
    essentiel
    -0.57
     ComVisible
    -0.53
     pareti
    -0.52
    copg
    -0.51
     tantum
    -0.49
     vooraf
    -0.49
     igång
    -0.49
     AssemblyProduct
    -0.48
    POSITIVE LOGITS
     new
    1.06
    新的
    1.05
     nuevas
    0.99
     nueva
    0.96
     nuevos
    0.96
    新しい
    0.93
    新
    0.93
     baru
    0.90
     새로운
    0.90
     nuevo
    0.88
    Activations Density 0.678%

    No Known Activations