© 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. 3325
    Prev
    Next
    INDEX
    Explanations

    articles and determiners in text

    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
     wireType
    -0.81
    findpost
    -0.81
     StatelessWidget
    -0.80
     Bly
    -0.77
    ा
    -0.77
    subplots
    -0.77
    coaster
    -0.77
    bø
    -0.77
     ffilmiau
    -0.74
    jsdelivr
    -0.73
    POSITIVE LOGITS
    Portale
    0.86
    ran
    0.76
     Anwar
    0.75
    cet
    0.73
    angen
    0.71
    lan
    0.70
    Ors
    0.70
     intern
    0.69
     an
    0.69
     Ors
    0.68
    Activations Density 2.098%

    No Known Activations