© 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. 11501
    Prev
    Next
    INDEX
    Explanations

    references to tablets and related devices

    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
    coroutines
    -0.74
    躇
    -0.69
     cha
    -0.66
     Cha
    -0.65
    unkel
    -0.65
     Este
    -0.65
     Dra
    -0.64
    ukunft
    -0.64
     Gu
    -0.64
     Lamar
    -0.62
    POSITIVE LOGITS
     Tablet
    1.45
     Tablets
    1.42
     tablet
    1.41
     tablets
    1.38
    tablet
    1.27
    Tablet
    1.26
     Pill
    1.22
     pill
    1.20
    Pill
    1.20
    pill
    1.15
    Activations Density 0.006%

    No Known Activations