© 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. 4-CLT-HP
    7. 1591
    Prev
    Next
    INDEX
    Explanations

    where which

    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
    nya
    -0.45
    :
    -0.43
    bindParam
    -0.43
     set
    -0.41
    ?
    -0.40
     in
    -0.36
    ly
    -0.35
     show
    -0.34
    hdashline
    -0.33
     you
    -0.33
    POSITIVE LOGITS
     فريبيس
    1.24
    expandindo
    1.12
     AssemblyCulture
    1.05
    verwijspagina
    1.03
     '\\;'
    1.02
     дописавши
    1.00
    StoryboardSegue
    0.91
    IntoConstraints
    0.89
    ValueStyle
    0.89
     &___
    0.89
    Activations Density 0.005%

    No Known Activations