© 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. 18083
    Prev
    Next
    INDEX
    Explanations

    certain conjunctions, modals, and expressions indicating necessity or probability

    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
     autorytatywna
    -0.84
    ècie
    -0.71
     متعلقه
    -0.67
    σμα
    -0.66
    elemField
    -0.65
    äischen
    -0.65
    rawDesc
    -0.65
     frequenza
    -0.64
    الإنجليزية
    -0.62
     blijkt
    -0.59
    POSITIVE LOGITS
    Личная
    0.43
     cellspacing
    0.41
    (__('
    0.41
    AutoScaleMode
    0.40
     orar
    0.39
    稠
    0.39
    NSIndexPath
    0.38
    Ikus
    0.37
     canta
    0.36
    webf
    0.36
    Activations Density 0.079%

    No Known Activations