© 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. 6046
    Prev
    Next
    INDEX
    Explanations

    mentions of problems or issues

    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
     questions
    -0.90
     question
    -0.85
    questions
    -0.80
     riddles
    -0.79
     Fragen
    -0.78
     Normdatei
    -0.77
    Questions
    -0.76
     Frage
    -0.75
     riddle
    -0.73
     matters
    -0.73
    POSITIVE LOGITS
     problem
    1.22
    problem
    1.16
     Problem
    1.13
    Problem
    1.09
     PROBLEM
    1.06
    PROBLEM
    0.89
     probleem
    0.81
     problema
    0.79
     problems
    0.77
     Problems
    0.77
    Activations Density 0.062%

    No Known Activations