© 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. 2836
    Prev
    Next
    INDEX
    Explanations

    references to statistical change or variation measurements

    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
    ChildScrollView
    -1.08
     purpoſe
    -1.05
     ſeveral
    -0.97
    fjspx
    -0.97
     Majefty
    -0.96
     ſte
    -0.96
     raiſ
    -0.96
     ſmall
    -0.95
     pleaſure
    -0.95
     myſelf
    -0.94
    POSITIVE LOGITS
     percent
    1.88
    percent
    1.49
     Percent
    1.27
    Percent
    1.15
     PERCENT
    1.05
     Prozent
    1.01
     procent
    0.87
    PERCENT
    0.86
     persen
    0.83
     ciento
    0.81
    Activations Density 0.015%

    No Known Activations