© 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. 18-RES-MATRYOSHKA-DC
    7. 173
    Prev
    Next
    INDEX
    Explanations

    legal jargon

    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.18.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.18.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
     
    -0.64
    ль
    -0.52
    -
    -0.52
     was
    -0.51
     flipped
    -0.50
     pulled
    -0.48
     tasked
    -0.48
    ’
    -0.48
     savvy
    -0.48
    stas
    -0.48
    POSITIVE LOGITS
     shall
    1.03
     églises
    0.97
     feroit
    0.94
     quaisquer
    0.93
    shall
    0.92
     prêtres
    0.90
     avoient
    0.89
    soever
    0.88
     quelcon
    0.88
     cesse
    0.87
    Activations Density 2.228%

    No Known Activations