© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3786
    Prev
    Next
    INDEX
    Explanations

    scientific/biological texts

    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
    CI
    -0.44
    ci
    -0.43
     peine
    -0.42
     
    -0.42
     Thompson
    -0.41
     ag
    -0.39
    iy
    -0.38
     nærm
    -0.38
     Rome
    -0.38
     no
    -0.38
    POSITIVE LOGITS
     ModelExpression
    0.81
     CreateTagHelper
    0.81
     tdci
    0.76
    parsedMessage
    0.75
    verwijspagina
    0.75
     дописавши
    0.73
     становника
    0.72
    AndEndTag
    0.71
    Diweddarwch
    0.70
    StoryboardSegue
    0.69
    Activations Density 0.007%

    No Known Activations