© 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. 9765
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their relationships, especially in the context of formulations and reactive materials

    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
     Efq
    -0.82
     myſelf
    -0.81
    WithIOException
    -0.72
     dépens
    -0.71
    seamnă
    -0.69
    ſelves
    -0.69
     stället
    -0.68
     itſelf
    -0.67
     quelcon
    -0.67
     féminine
    -0.67
    POSITIVE LOGITS
     triple
    0.62
    ọi
    0.60
    ligen
    0.59
     ↑
    0.56
    dit
    0.56
     “
    0.54
     mo
    0.54
     Te
    0.53
     dit
    0.52
     ver
    0.51
    Activations Density 0.258%

    No Known Activations