© 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. 5873
    Prev
    Next
    INDEX
    Explanations

    references to percentages or proportions

    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
    OGND
    -0.99
     Roskov
    -0.97
     AssemblyCompany
    -0.88
     doInBackground
    -0.86
    
    -0.85
     ProductService
    -0.84
    AutoField
    -0.81
    principalColumn
    -0.81
    Portale
    -0.79
     оригіналу
    -0.79
    POSITIVE LOGITS
     percentage
    2.33
     Percentage
    1.95
    percentage
    1.92
    Percentage
    1.91
     percentages
    1.80
     porcentaje
    1.50
     pourcentage
    1.38
    百分
    1.17
    PERCENT
    1.06
     PERCENT
    1.05
    Activations Density 0.007%

    No Known Activations