© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5499
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal background and living arrangements

    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
     transférez
    -0.47
    рите
    -0.46
    gmd
    -0.44
     pierdas
    -0.43
     trat
    -0.43
    lcccc
    -0.43
     counters
    -0.42
    engelsk
    -0.41
    lrrrr
    -0.41
    istad
    -0.41
    POSITIVE LOGITS
     resided
    0.92
     residence
    0.88
    Datuak
    0.85
     resides
    0.85
     residing
    0.81
     reside
    0.81
    ménage
    0.81
     relocation
    0.80
     pinulongan
    0.79
     abode
    0.79
    Activations Density 0.284%

    No Known Activations