© 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. 6110
    Prev
    Next
    INDEX
    Explanations

    programming terms and technical references

    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
    /***/
    -0.58
    saraba
    -0.54
     Italijani
    -0.54
     GetEnumerator
    -0.49
    zuli
    -0.45
    farin
    -0.45
    ėse
    -0.44
    ANSA
    -0.44
    Filmographie
    -0.44
     respon
    -0.43
    POSITIVE LOGITS
    Instead
    0.77
     Instead
    0.73
    UserScript
    0.68
    URLException
    0.67
     instead
    0.66
    代わりに
    0.65
     alternatives
    0.64
    instead
    0.64
    rungsseite
    0.64
    mergeFrom
    0.60
    Activations Density 0.822%

    No Known Activations