© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15079
    Prev
    Next
    INDEX
    Explanations

    references to specific high-rated words indicating evaluation or emphasis, particularly emphasizing particular concepts or actions

    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
    NUMX
    -1.06
     XNUMX
    -0.98
     ciasc
    -0.94
     stället
    -0.85
     whoſe
    -0.84
     ainfi
    -0.82
     särskilt
    -0.75
     plufieurs
    -0.75
     särsk
    -0.75
     |
    -0.73
    POSITIVE LOGITS
     definately
    1.06
     loosing
    0.93
     diatas
    0.90
    に於
    0.90
     alot
    0.86
    Whilst
    0.84
     dependant
    0.81
     Whilst
    0.79
     للمعارف
    0.79
     aprox
    0.79
    Activations Density 2.647%

    No Known Activations