© 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. 12-RES-MATRYOSHKA-DC
    7. 25369
    Prev
    Next
    INDEX
    Explanations

    the letter 'h' in various contexts

    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
    Negative Logits
    expandindo
    -0.79
    ſelf
    -0.71
     raiſ
    -0.68
     Efq
    -0.65
     للاسماء
    -0.64
    opic
    -0.63
     unſ
    -0.60
     pleaſure
    -0.60
     Anſ
    -0.60
     myſelf
    -0.59
    POSITIVE LOGITS
    prefixer
    0.75
    AddHtmlAttribute
    0.74
     textStatus
    0.69
     récompenses
    0.64
    addPreferredGap
    0.62
    Linki
    0.60
     bénéfices
    0.60
    dération
    0.59
    AddTagHelper
    0.57
     IBOutlet
    0.57
    Activations Density 0.005%

    No Known Activations