© 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. 10919
    Prev
    Next
    INDEX
    Explanations

    references to quantities of weight or mass

    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
     inches
    -1.04
    MigrationBuilder
    -0.81
     Inches
    -0.73
    inches
    -0.71
     OFDb
    -0.71
    $_['
    -0.70
     OMITBAD
    -0.68
     inch
    -0.67
     "..\..\..\
    -0.66
    findpost
    -0.65
    POSITIVE LOGITS
     pound
    2.95
     Pound
    2.66
    Pound
    2.61
    pound
    2.53
    POUND
    1.38
     pounding
    1.34
     pounded
    1.33
     dollar
    1.03
    pounds
    1.00
     pounds
    0.94
    Activations Density 0.002%

    No Known Activations