© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40368
    Prev
    Next
    INDEX
    Explanations

    surname

    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
    ::
    -0.78
    ly
    -0.72
    ::_
    -0.53
    LY
    -0.52
    ened
    -0.52
    ofer
    -0.52
     destination
    -0.50
    ish
    -0.48
    zard
    -0.46
    Dzi
    -0.46
    POSITIVE LOGITS
    phrine
    0.75
    UrlResolution
    0.73
     AppBundle
    0.66
     BoxFit
    0.66
    IBarButtonItem
    0.66
     AssemblyTitle
    0.64
     laſt
    0.64
     Alamy
    0.63
    ,‎
    0.63
    Rujuakan
    0.63
    Activations Density 0.069%

    No Known Activations