© 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. 11969
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     purpoſe
    -0.71
     myſelf
    -0.71
     Monfieur
    -0.65
    labelledby
    -0.64
     pleaſure
    -0.62
    anganese
    -0.60
     iſt
    -0.60
     EconPapers
    -0.59
     Shakspeare
    -0.59
    RunWith
    -0.58
    POSITIVE LOGITS
    大
    3.19
    小
    1.92
     大
    1.89
    的大
    1.43
    が大
    1.29
    ⼤
    1.23
    是大
    1.23
     小
    1.22
    の大
    1.20
    在大
    1.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.