© 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. 14942
    Prev
    Next
    INDEX
    Explanations

    quantitative data or statistics related to outcomes or effects in research studies

    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
     Taktlose
    -0.75
     beginnetje
    -0.61
    parsedMessage
    -0.61
     intptr
    -0.58
    Geplaatst
    -0.55
    MessageOf
    -0.54
    NameInMap
    -0.52
     فريبيس
    -0.52
    SharedCtor
    -0.51
    دانشنامهٔ
    -0.50
    POSITIVE LOGITS
    endphp
    0.76
     grève
    0.63
    quartered
    0.60
     useHistory
    0.59
    itans
    0.58
    IMPORTED
    0.57
    PostExecute
    0.56
    bkz
    0.56
     genomen
    0.56
    lielmo
    0.56
    Activations Density 0.011%

    No Known Activations