© 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. 3012
    Prev
    Next
    INDEX
    Explanations

    the word "inspiration"

    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
    oporosis
    -0.66
    WAUKEE
    -0.65
    gdala
    -0.65
    OGND
    -0.65
    CodeAttribute
    -0.64
    Istorija
    -0.64
    omaly
    -0.62
    WebVitals
    -0.62
    savevideo
    -0.61
    amazonaws
    -0.61
    POSITIVE LOGITS
     inspiration
    2.89
     Inspiration
    2.56
    Inspiration
    2.45
    inspiration
    2.41
     inspirations
    2.39
     inspired
    2.33
     inspira
    2.31
     inspire
    2.22
     inspir
    2.17
     Inspired
    2.13
    Activations Density 0.027%

    No Known Activations