© 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. 4-CLT-HP
    7. 927
    Prev
    Next
    INDEX
    Explanations

    3

    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
     jScrollPane
    -0.57
    pry
    -0.54
    ViewChild
    -0.53
    htra
    -0.47
     surpren
    -0.47
    hibernate
    -0.47
    iedene
    -0.46
    læg
    -0.46
    endregion
    -0.46
    ficação
    -0.46
    POSITIVE LOGITS
     Meksiku
    0.69
     betweenstory
    0.68
    ThroughAttribute
    0.65
    verwijspagina
    0.62
     lenker
    0.59
     '\\;'
    0.59
     kasarigan
    0.59
    GraphicsUnit
    0.57
     dAtA
    0.57
    UrlResolution
    0.56
    Activations Density 0.004%

    No Known Activations