© 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. 22-RES-MATRYOSHKA-DC
    7. 2266
    Prev
    Next
    INDEX
    Explanations

    interjections, interjections, and emoticons

    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
     sir
    -0.69
     dear
    -0.68
    sir
    -0.65
    EndContext
    -0.64
    dear
    -0.61
     gentlemen
    -0.60
     sweetie
    -0.59
    DEAR
    -0.58
     sweetheart
    -0.57
    Gentlemen
    -0.57
    POSITIVE LOGITS
    LookAnd
    0.65
     дописавши
    0.56
    MigrationBuilder
    0.54
     éc
    0.54
     idk
    0.51
     Idk
    0.50
     ویکی‌پدی
    0.50
    eah
    0.50
    ыгана
    0.48
     SwitchCompat
    0.48
    Activations Density 0.108%

    No Known Activations