© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4706
    Prev
    Next
    INDEX
    Explanations

    code structure related to class definitions and method implementations in programming

    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
     myſelf
    -1.03
     Efq
    -1.01
     uſed
    -0.96
     itſelf
    -0.96
     themſelves
    -0.94
     houſe
    -0.93
     purpoſe
    -0.92
     Jefus
    -0.91
     Majefty
    -0.88
     Monfieur
    -0.88
    POSITIVE LOGITS
     os
    0.42
    FieldNumber
    0.42
    <eos>
    0.41
     
    0.41
    ugh
    0.40
     so
    0.40
     Gas
    0.40
     S
    0.39
     exclusive
    0.39
    so
    0.39
    Activations Density 0.346%

    No Known Activations