© 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. 354
    Prev
    Next
    INDEX
    Explanations

    significant emotional experiences or pivotal moments in life narratives

    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
    Autoritní
    -1.20
     autorytatywna
    -1.05
    IUrlHelper
    -0.98
    })*/
    -0.94
     NSCoder
    -0.93
    $_['
    -0.93
    انيف
    -0.91
    ReusableCell
    -0.91
    ]-'
    -0.91
    parsedMessage
    -0.91
    POSITIVE LOGITS
    .
    0.46
    Moreover
    0.43
    ?
    0.43
    But
    0.40
    However
    0.40
    Furthermore
    0.39
    Specifically
    0.39
    cue
    0.38
    Residue
    0.38
    Ironically
    0.38
    Activations Density 1.007%

    No Known Activations