© 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. 1-CLT-HP
    7. 15714
    Prev
    Next
    INDEX
    Explanations

    physics/launching

    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
     Fishes
    -0.75
    Portale
    -0.66
    jeune
    -0.57
     Against
    -0.55
    folger
    -0.53
     púb
    -0.52
    γέν
    -0.52
     AspNetCore
    -0.50
     fishes
    -0.50
     Manufac
    -0.50
    POSITIVE LOGITS
    rrggbb
    0.56
     Савезне
    0.55
    onAttach
    0.54
     OMITBAD
    0.48
    存于互联网档案馆
    0.48
    TableModel
    0.47
    MLLoader
    0.47
    exitRule
    0.46
    webElementXpaths
    0.46
     text
    0.46
    Activations Density 0.050%

    No Known Activations