© 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. 11284
    Prev
    Next
    INDEX
    Explanations

    terms related to memory and the concept of remembering

    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
     '\\;'
    -0.66
     perche
    -0.61
     Paglinawan
    -0.60
    __(/*!
    -0.59
    vermectin
    -0.56
     eût
    -0.55
     cuándo
    -0.53
     nødvendig
    -0.53
    volve
    -0.52
     atlik
    -0.52
    POSITIVE LOGITS
     DbType
    0.83
    ValueStyle
    0.81
     referenties
    0.80
    %)$
    0.72
     NSCoder
    0.72
     oprot
    0.71
    rungsseite
    0.70
     كومونز
    0.68
    Memories
    0.68
    ]]);
    0.68
    Activations Density 0.007%

    No Known Activations