© 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. 417
    Prev
    Next
    INDEX
    Explanations

    phrases that identify the main point or the most important aspect of something.

    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
    __":
    -0.59
    torie
    -0.56
    MLLoader
    -0.56
    MigrationBuilder
    -0.55
     >=",
    -0.54
    Personensuche
    -0.52
    ouple
    -0.51
    unnitel
    -0.51
     tertentu
    -0.51
     snippetHide
    -0.51
    POSITIVE LOGITS
     source
    1.20
     cornerstone
    1.01
     catalyst
    0.97
    source
    0.96
     key
    0.96
     basis
    0.94
     principale
    0.94
     mainstay
    0.93
     main
    0.93
     tool
    0.93
    Activations Density 2.557%

    No Known Activations