© 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. 12-RES-MATRYOSHKA-DC
    7. 22916
    Prev
    Next
    INDEX
    Explanations

    expressions of embarrassment, shame, and humiliation

    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
    fillType
    -0.75
    WithIOException
    -0.73
    kuuta
    -0.69
    FormTagHelper
    -0.68
    MigrationBuilder
    -0.68
    ChromeDriver
    -0.66
     AssemblyCulture
    -0.65
    Искәрмәләр
    -0.64
    PreferredItem
    -0.60
    UnusedPrivate
    -0.59
    POSITIVE LOGITS
     embarrassment
    1.15
     embarrassed
    1.12
    Embar
    1.11
    embar
    1.09
     Embar
    1.09
     shame
    1.04
     embarrass
    1.04
    shame
    1.00
     embarrassing
    0.99
     disgrace
    0.98
    Activations Density 0.021%

    No Known Activations