© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13537
    Prev
    Next
    INDEX
    Explanations

    the estimator that minimizes a specific moment condition

    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
    cuerdo
    -0.72
    '])->
    -0.72
    ']").
    -0.70
    /*
    -0.69
     مرئيه
    -0.69
    '):
    
    -0.65
    }*/
    
    -0.63
    antaranya
    -0.63
    ]--;
    -0.63
     houſe
    -0.63
    POSITIVE LOGITS
     estimator
    3.03
     estimators
    2.48
     Esti
    1.86
    estimator
    1.70
    Estimator
    1.36
    estimators
    1.11
    Esti
    0.84
    ckeye
    0.60
    dekor
    0.57
    стье
    0.52
    Activations Density 0.010%

    No Known Activations