© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 1467
    Prev
    Next
    INDEX
    Explanations

    phrases containing 'as', 'to', 'the', 'a', 'an', 'be', and 'equal'.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    脚注の使い方
    -0.78
    ########.
    -0.73
    ंदीखरीदारी
    -0.72
     iprot
    -0.65
     uſe
    -0.61
     pleaſure
    -0.61
     purpoſe
    -0.59
    !*\
    -0.59
     detected
    -0.57
    setVerticalGroup
    -0.57
    POSITIVE LOGITS
     étant
    1.05
     fiind
    0.85
    étant
    0.75
     tendo
    0.75
     having
    0.74
     being
    0.73
     sendo
    0.71
     needing
    0.71
     "
    0.69
     belonging
    0.69
    Activations Density 0.425%

    No Known Activations