© 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. 3-RES-MATRYOSHKA-DC
    7. 2961
    Prev
    Next
    INDEX
    Explanations

    the word "fluorescence"

    oai_token-act-pair · gemini-2.0-flash
    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
    AndEndTag
    -0.79
     Normdatei
    -0.65
    Portály
    -0.63
     Caspian
    -0.63
     ivelany
    -0.59
     Rask
    -0.59
    fone
    -0.58
     spa
    -0.57
     batter
    -0.56
     TextInputType
    -0.56
    POSITIVE LOGITS
     fluorescence
    2.81
     Fluorescence
    2.56
     fluorescent
    2.23
    Fluorescence
    2.22
    orescence
    2.14
     Fluorescent
    2.09
    orescent
    2.06
     fluores
    1.73
    荧
    1.43
    ofluorescence
    1.34
    Activations Density 0.007%

    No Known Activations