© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 2656
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers related to legal or official documents

    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
     Cor
    -0.66
    CreateMap
    -0.65
    2
    -0.65
     Krueger
    -0.62
     Tr
    -0.61
     
    -0.60
    <em>
    -0.58
     Mar
    -0.58
    1
    -0.58
    <eos>
    -0.57
    POSITIVE LOGITS
    Datuak
    1.27
     myſelf
    1.15
     doInBackground
    1.14
     kaynağından
    1.09
     raiſ
    1.05
    }();
    1.05
     faſt
    1.01
     occaf
    1.00
     uſed
    1.00
     iconFacebook
    0.99
    Activations Density 0.715%

    No Known Activations