© 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. 1-RES-MATRYOSHKA-DC
    7. 950
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings involving motions, orders, or appeals

    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
     فريبيس
    -0.66
    ftagPool
    -0.60
     canon
    -0.54
    aguars
    -0.54
     हुई
    -0.53
     clause
    -0.53
    leb
    -0.53
    ]=>
    -0.52
     jurors
    -0.51
    kni
    -0.51
    POSITIVE LOGITS
     onCreateView
    0.81
     חיצוניים
    0.79
     CURIAM
    0.76
    Appellant
    0.73
     createState
    0.67
    saraba
    0.65
    AutoScaleMode
    0.64
     Appellee
    0.64
    
    0.62
     autorytatywna
    0.61
    Activations Density 1.651%

    No Known Activations