© 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. 0-CLT-HP
    7. 42832
    Prev
    Next
    INDEX
    Explanations

    scientific/biological terms

    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
     organisms
    -0.59
     containing
    -0.58
     transport
    -0.55
    providedIn
    -0.55
    fara
    -0.50
     contener
    -0.50
    escape
    -0.48
    iyle
    -0.48
    ed
    -0.47
    ing
    -0.47
    POSITIVE LOGITS
    twimg
    0.78
    IsContent
    0.74
    sizeCache
    0.68
     ISTAT
    0.68
    ParallelGroup
    0.65
     يتيمه
    0.64
     estekak
    0.59
     pinulongan
    0.59
    InjectAttribute
    0.59
     <>",
    0.56
    Activations Density 0.416%

    No Known Activations