© 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. 2-RES-MATRYOSHKA-DC
    7. 6441
    Prev
    Next
    INDEX
    Explanations

    references to quantity or magnitude

    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
    far
    -0.68
     ganske
    -0.59
    Quite
    -0.56
     ganska
    -0.53
     quite
    -0.52
     Quite
    -0.51
    Many
    -0.51
    Far
    -0.50
    quite
    -0.49
     far
    -0.49
    POSITIVE LOGITS
    principalTable
    1.09
    AddTagHelper
    1.00
     estekak
    0.96
     disambiguazione
    0.87
    彿
    0.84
    excess
    0.80
     CURIAM
    0.77
     ModelExpression
    0.76
     much
    0.76
     Excess
    0.76
    Activations Density 0.090%

    No Known Activations