© 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. 22-RES-MATRYOSHKA-DC
    7. 3108
    Prev
    Next
    INDEX
    Explanations

    verbs associated with positive emotions or the start of actions

    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.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    MetaObject
    -0.50
    <bos>
    -0.50
    اته
    -0.49
    She
    -0.47
    /-/
    -0.46
    He
    -0.46
    اتها
    -0.45
     He
    -0.44
    /***/
    -0.43
    kolwiek
    -0.42
    POSITIVE LOGITS
     former
    1.41
    Former
    1.22
    former
    1.22
     longtime
    1.21
     actor
    1.16
     Former
    1.13
     actress
    1.13
     veteran
    1.12
     comedian
    1.09
     fellow
    1.09
    Activations Density 0.627%

    No Known Activations