© 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. 32241
    Prev
    Next
    INDEX
    Explanations

    references to guidelines or standards in various contexts

    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
    MatButtonModule
    -0.77
    byshire
    -0.67
    solete
    -0.66
     ویکی‌پدیا
    -0.66
     Dent
    -0.66
     Tob
    -0.66
    ckså
    -0.66
    sikker
    -0.64
     cong
    -0.63
    uspiel
    -0.63
    POSITIVE LOGITS
     guideline
    0.93
     Guidelines
    0.89
     guidelines
    0.79
     Guideline
    0.79
    Guidelines
    0.78
     információk
    0.77
     Drapeau
    0.76
     GUIDELINES
    0.75
     iprot
    0.64
    derry
    0.64
    Activations Density 0.003%

    No Known Activations