© 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. 26726
    Prev
    Next
    INDEX
    Explanations

    comedic or humorous elements in the text

    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
     kasarigan
    -0.67
    
    -0.63
    ApiOperation
    -0.58
    jsdelivr
    -0.57
    djangoproject
    -0.55
    ERVIS
    -0.53
    shadowOffset
    -0.49
    ThroughAttribute
    -0.49
    "?>
    -0.47
     Mø
    -0.47
    POSITIVE LOGITS
    </caption>
    0.68
    󠁢
    0.61
    抱
    0.60
    γά
    0.60
     standing
    0.59
    цездатний
    0.58
    hasData
    0.58
     résister
    0.58
    괄
    0.57
    PerformLayout
    0.57
    Activations Density 0.005%

    No Known Activations