© 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. 20004
    Prev
    Next
    INDEX
    Explanations

    words related to serving or assistance

    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
    dė
    -0.70
     service
    -0.68
    atical
    -0.68
    plained
    -0.67
    endif
    -0.66
     Service
    -0.65
    Serviço
    -0.63
    ísimo
    -0.63
    Köszönöm
    -0.62
    hoga
    -0.60
    POSITIVE LOGITS
     createSlice
    1.16
    NameInMap
    1.09
     Serves
    0.88
     serves
    0.86
     served
    0.84
     serve
    0.83
     Serve
    0.82
    served
    0.81
    Serve
    0.80
    serving
    0.78
    Activations Density 0.018%

    No Known Activations