© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45474
    Prev
    Next
    INDEX
    Explanations

    fundraising

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fund
    -1.01
     fundraising
    -0.90
     fundraiser
    -0.87
     raise
    -0.82
     raising
    -0.77
     raises
    -0.71
    Fundraising
    -0.71
    fund
    -0.68
     advancing
    -0.68
     Fundraising
    -0.65
    POSITIVE LOGITS
    ########.
    0.68
     Cæsar
    0.65
     itſelf
    0.63
     Shakspeare
    0.63
     poffe
    0.62
     оригіналу
    0.57
     equiv
    0.56
     virginity
    0.56
     migh
    0.55
     Penta
    0.55
    Activations Density 0.267%

    No Known Activations