© 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. 24567
    Prev
    Next
    INDEX
    Explanations

    strong language and expressions of frustration or anger

    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
    Not in Any Lists

    No Comments

    Negative Logits
     sähkö
    -0.73
    område
    -0.70
     Kecil
    -0.63
     cadeaux
    -0.63
     pertes
    -0.63
     střed
    -0.62
     tronco
    -0.60
     coupable
    -0.60
    ungkapkan
    -0.59
     idéia
    -0.59
    POSITIVE LOGITS
     insuffisamment
    0.79
    ))->
    0.77
     damn
    0.76
     bloody
    0.75
     freaking
    0.74
    Fuckin
    0.73
     damned
    0.69
    ArrayOf
    0.69
     dam
    0.69
     fucking
    0.68
    Activations Density 0.002%

    No Known Activations