© 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. 20-CLT-HP
    7. 71824
    Prev
    Next
    INDEX
    Explanations

    medical/scientific publication

    np_max-act-logits · 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
     betweenstory
    -0.66
     Nice
    -0.52
     Beau
    -0.51
     Renoir
    -0.51
    libft
    -0.50
    Nice
    -0.48
     Bad
    -0.48
     fair
    -0.48
     Ade
    -0.48
    stdafx
    -0.48
    POSITIVE LOGITS
     estekak
    0.60
    Tembelea
    0.55
    Autoritní
    0.53
     виправивши
    0.52
     ligiloj
    0.51
    ьаж
    0.51
    HEAST
    0.50
     getItemId
    0.49
     дописавши
    0.49
    thâu
    0.49
    Activations Density 0.001%

    No Known Activations