© 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. 11108
    Prev
    Next
    INDEX
    Explanations

    symbols or formatting in the text

    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
    ſelves
    -0.70
    theless
    -0.70
    etheless
    -0.69
    esterday
    -0.64
    DataAnnotations
    -0.63
     Eche
    -0.61
    \{\\
    -0.60
    >\<^
    -0.59
    phans
    -0.59
    MEMOR
    -0.59
    POSITIVE LOGITS
    WithIOException
    0.74
    MeasureSpec
    0.70
    mybatisplus
    0.64
     دیکھیے
    0.63
    Personensuche
    0.57
    ArrowToggle
    0.57
    الحياه
    0.55
    AccessorTable
    0.54
    +#+
    0.53
    icoot
    0.52
    Activations Density 0.021%

    No Known Activations