© 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. 20771
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" and related conjunctions

    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
    ContentAsync
    -0.99
    Geplaatst
    -0.91
    DockStyle
    -0.81
    Diweddarwch
    -0.77
     AssemblyCompany
    -0.75
     cherchés
    -0.74
     autorytatywna
    -0.74
    Démographie
    -0.73
    +#+
    -0.72
    migrationBuilder
    -0.71
    POSITIVE LOGITS
    ambique
    0.52
     meisjes
    0.47
    期
    0.44
    guerite
    0.42
     komende
    0.42
    diging
    0.42
    di
    0.42
    Gypsy
    0.41
     situatie
    0.41
    be
    0.39
    Activations Density 0.219%

    No Known Activations