© 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. 3648
    Prev
    Next
    INDEX
    Explanations

    patterns related to size comparisons and array operations

    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
     themſelves
    -0.78
     itſelf
    -0.72
     whoſe
    -0.72
    })*/
    -0.69
     myſelf
    -0.67
     ſtate
    -0.65
     financières
    -0.65
     fallu
    -0.64
     becauſe
    -0.62
     sanitaires
    -0.62
    POSITIVE LOGITS
    ReadLine
    0.78
    fetchone
    0.73
     getItemId
    0.69
    trim
    0.64
    parseFrom
    0.63
    AnchorStyles
    0.63
    fetchall
    0.62
    OrWhiteSpace
    0.62
     hashCode
    0.61
    GetEnumerator
    0.61
    Activations Density 0.323%

    No Known Activations