© 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. 12-RES-MATRYOSHKA-DC
    7. 4932
    Prev
    Next
    INDEX
    Explanations

    conversational phrases that introduce or respond to statements

    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
     Roskov
    -1.07
    rungsseite
    -0.92
    TagMode
    -0.89
    homonymie
    -0.87
    RegressionTest
    -0.85
    LEncoder
    -0.84
     للمعارف
    -0.77
     виправивши
    -0.76
    SpringRunner
    -0.75
    derry
    -0.75
    POSITIVE LOGITS
     Well
    0.91
    Well
    0.91
     well
    0.70
     WELL
    0.68
    Pues
    0.63
    well
    0.63
     Ну
    0.60
     Wells
    0.54
    wells
    0.54
    }`}>
    0.53
    Activations Density 0.023%

    No Known Activations