© 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. 40414
    Prev
    Next
    INDEX
    Explanations

    phosphate

    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
    issa
    -0.64
    rios
    -0.63
    phosphate
    -0.62
    rungsseite
    -0.60
     phosphate
    -0.60
     Wikimedijinoj
    -0.57
    IndentedString
    -0.54
    psis
    -0.54
    ISSA
    -0.53
     CURIAM
    -0.52
    POSITIVE LOGITS
     useAuth
    0.73
    InjectMocks
    0.69
    epam
    0.63
     onAnimation
    0.61
    erapa
    0.60
     handker
    0.59
     AppColors
    0.59
     SDLK
    0.57
    s
    0.57
     therefrom
    0.57
    Activations Density 0.197%

    No Known Activations