© 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. 2-RES-MATRYOSHKA-DC
    7. 5398
    Prev
    Next
    INDEX
    Explanations

    words that convey a sense or feeling of perception or understanding

    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
     Sensitive
    -1.33
     sensitive
    -1.31
    sensitive
    -1.27
     sensitivity
    -1.25
     Sensitivity
    -1.24
    Sensitive
    -1.22
    sensitivity
    -1.16
    Sensitivity
    -1.15
     sensitivities
    -1.13
    ensitive
    -0.97
    POSITIVE LOGITS
     sense
    2.95
    sense
    2.53
     Sense
    2.45
     SENSE
    2.28
    Sense
    2.13
     sentido
    1.65
     senso
    1.34
     senses
    1.31
     sentidos
    1.01
     Sinne
    0.98
    Activations Density 0.015%

    No Known Activations