© 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. 1089
    Prev
    Next
    INDEX
    Explanations

    the string "A[something]P" and references or citations

    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
    queles
    -0.71
    quilo
    -0.65
    quela
    -0.64
     affrontare
    -0.58
     też
    -0.56
     springfox
    -0.55
    FXMLLoader
    -0.55
    InitVars
    -0.54
    NamedQueries
    -0.53
    rary
    -0.50
    POSITIVE LOGITS
     aVar
    0.56
     href
    0.54
    aA
    0.51
    aaaa
    0.50
     few
    0.48
     crossorigin
    0.48
    aaa
    0.47
    on
    0.47
     great
    0.46
    fair
    0.45
    Activations Density 0.742%

    No Known Activations