© 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. 10996
    Prev
    Next
    INDEX
    Explanations

    references to the examiner conducting official reviews or decisions

    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
    tableFuture
    -0.54
    تص
    -0.50
     poche
    -0.49
    reszcie
    -0.45
     trifft
    -0.45
    Ma
    -0.45
     imidlertid
    -0.45
    abetta
    -0.44
    פתח
    -0.44
     pau
    -0.43
    POSITIVE LOGITS
     examiner
    3.61
     Examiner
    3.55
     examiners
    2.66
     Examiners
    2.44
    examiner
    2.28
     EXAMIN
    1.46
     assessor
    0.97
     propOrder
    0.87
    Exam
    0.84
     assessors
    0.80
    Activations Density 0.001%

    No Known Activations