© 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. 0-RES-MATRYOSHKA-DC
    7. 11835
    Prev
    Next
    INDEX
    Explanations

    references to a specific name or term, which in this case is "ved"

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.63
     slip
    -0.55
    ;'>
    -0.54
     pinulongan
    -0.52
    iprot
    -0.52
    发表于
    -0.51
    ISupport
    -0.51
    KommentareTeilen
    -0.50
     jScrollPane
    -0.50
    ($__
    -0.50
    POSITIVE LOGITS
     ved
    3.39
     Ved
    2.48
    Ved
    2.31
     VED
    1.48
     veda
    1.16
     vede
    0.85
     Veda
    0.82
     Vedic
    0.81
     Vedas
    0.80
    vedic
    0.71
    Activations Density 0.000%

    No Known Activations