© 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. 24-RES-MATRYOSHKA-DC
    7. 662
    Prev
    Next
    INDEX
    Explanations

    words related to regulatory compliance, verification, safety, and/or proper functioning of something

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
     kasarigan
    -0.72
     esternos
    -0.65
    Schedulers
    -0.65
     referrerpolicy
    -0.65
     énorm
    -0.65
     nakalista
    -0.65
    Pautan
    -0.64
    Huge
    -0.63
     GenerationType
    -0.62
    sizeCache
    -0.62
    POSITIVE LOGITS
     proper
    1.88
     correct
    1.82
     properly
    1.77
     correctly
    1.70
     adequate
    1.70
     satisfactory
    1.68
     appropriate
    1.59
     acceptable
    1.56
     accurate
    1.52
     adequately
    1.46
    Activations Density 3.427%

    No Known Activations