© 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. 6237
    Prev
    Next
    INDEX
    Explanations

    references to various "forms" or "types" in a textual context

    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
    Negative Logits
    AJAS
    -0.82
     Keegan
    -0.80
     متعلقه
    -0.79
     NCC
    -0.79
    pædia
    -0.77
     Gä
    -0.77
     arbitrage
    -0.77
     Bracken
    -0.76
     cellpadding
    -0.75
    wyczaj
    -0.75
    POSITIVE LOGITS
     FORM
    1.66
     Forms
    1.56
     Form
    1.55
    Form
    1.47
     FORMS
    1.45
    form
    1.41
    FORM
    1.39
    Forms
    1.38
     forms
    1.38
    forms
    1.37
    Activations Density 0.133%

    No Known Activations