© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 902
    Prev
    Next
    INDEX
    Explanations

    a sequence of connector words like "and", "but", "or", followed by punctuation and/or common short words

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    __(/*!
    -0.71
    expandindo
    -0.59
    værende
    -0.58
    Erreferentziak
    -0.56
    оборот
    -0.54
    memset
    -0.53
    дует
    -0.52
    lné
    -0.52
    fatalError
    -0.51
    uç
    -0.49
    POSITIVE LOGITS
     then
    4.50
    then
    3.66
    Then
    3.59
     Then
    3.58
     THEN
    3.27
    THEN
    2.91
     kemudian
    2.73
     سپس
    2.73
     entonces
    2.61
     затем
    2.61
    Activations Density 2.998%

    No Known Activations