© 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. 22265
    Prev
    Next
    INDEX
    Explanations

    references to experts and expertise

    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
    Naissance
    -0.90
    skills
    -0.84
    skilled
    -0.84
    Autoritní
    -0.81
     Skilled
    -0.77
    ValueStyle
    -0.73
     technics
    -0.72
     skilled
    -0.72
     Pho
    -0.71
    TECHN
    -0.71
    POSITIVE LOGITS
    putExtra
    0.73
    DIPSETTING
    0.70
    います
    0.67
    urts
    0.66
    artik
    0.66
    djangoproject
    0.65
     witnesses
    0.61
     ordf
    0.61
    pert
    0.60
    consumo
    0.59
    Activations Density 0.008%

    No Known Activations