© 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. 30935
    Prev
    Next
    INDEX
    Explanations

    HTML or JavaScript source file 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
    ↵
    -0.50
     was
    -0.47
    خم
    -0.44
    ,
    -0.42
     бес
    -0.42
    WriteAttribute
    -0.42
     he
    -0.41
     وی
    -0.40
     to
    -0.39
    .
    -0.38
    POSITIVE LOGITS
    NameInMap
    1.03
    hynch
    0.87
     NgModule
    0.86
    MockBean
    0.86
     MotionEvent
    0.80
    twimg
    0.78
    moiselle
    0.78
    celotti
    0.77
     IMDb
    0.77
     src
    0.76
    Activations Density 0.001%

    No Known Activations