© 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. 43109
    Prev
    Next
    INDEX
    Explanations

    person

    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
     person
    -0.73
    حياته
    -0.59
    حياتها
    -0.52
     Person
    -0.51
     useDispatch
    -0.50
     thing
    -0.49
     createSprite
    -0.48
     verksamhet
    -0.48
     useSelector
    -0.47
    WriteAttribute
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    0.75
     communiquez
    0.73
    Diweddarwch
    0.71
     Roskov
    0.67
    <bos>
    0.64
    ViewFeatures
    0.63
    
    0.62
     AssemblyCulture
    0.61
    ⓘ
    0.59
    ']):
    0.59
    Activations Density 0.090%

    No Known Activations