© 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. 24-RES-MATRYOSHKA-DC
    7. 1580
    Prev
    Next
    INDEX
    Explanations

    verbs, especially those related to seeking assistance, interactions, or emotional responses in conversations.

    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.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     euch
    -0.55
    InputBorder
    -0.52
    AddTagHelper
    -0.49
    WE
    -0.49
    给他们
    -0.48
     BoxDecoration
    -0.47
    expandindo
    -0.46
     InputDecoration
    -0.46
     Euch
    -0.45
    Попис
    -0.45
    POSITIVE LOGITS
     me
    3.61
    me
    1.75
     мне
    1.66
     mnie
    1.64
     меня
    1.63
     conmigo
    1.63
     comigo
    1.50
     मुझे
    1.48
     мной
    1.45
     Me
    1.38
    Activations Density 0.441%

    No Known Activations