© 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. 15216
    Prev
    Next
    INDEX
    Explanations

    references to mathematical norms

    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
     Scherer
    -0.81
     Rosal
    -0.78
    合衆
    -0.77
     Phelps
    -0.75
     pittura
    -0.72
     Heidelberg
    -0.70
    Hauptartikel
    -0.70
    </i>
    -0.69
     Spal
    -0.69
     Stapleton
    -0.69
    POSITIVE LOGITS
     norm
    1.23
    norm
    1.14
     Norm
    1.14
     norms
    1.11
    Norm
    1.09
    norms
    0.92
    ArrowToggle
    0.84
     normative
    0.83
     NORM
    0.82
    NORM
    0.77
    Activations Density 0.007%

    No Known Activations