© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19759
    Prev
    Next
    INDEX
    Explanations

    individual letters or characters used in formatting or special symbols

    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
     resourceCulture
    -0.77
    zerland
    -0.65
     doInBackground
    -0.63
    :✨
    -0.60
     للاسماء
    -0.60
     piattaforma
    -0.57
     masina
    -0.56
    HostException
    -0.55
    ponent
    -0.55
     GetEnumerator
    -0.54
    POSITIVE LOGITS
     Wikimedijinoj
    0.63
    UserScript
    0.56
     DbSet
    0.53
     moe
    0.52
     CASO
    0.50
    DoubleQuotes
    0.50
    UnusedPrivate
    0.49
     Мексичка
    0.49
    Brainz
    0.47
     PyLong
    0.47
    Activations Density 0.017%

    No Known Activations