© 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. 9480
    Prev
    Next
    INDEX
    Explanations

    number

    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
    脚注の使い方
    -0.78
    رشف
    -0.76
    sizeCache
    -0.75
     nakalista
    -0.75
     CreateTagHelper
    -0.75
    IndentedString
    -0.72
     disambiguazione
    -0.72
    featureID
    -0.68
     autorytatywna
    -0.68
     nahilalakip
    -0.68
    POSITIVE LOGITS
    =#{
    0.43
    insics
    0.42
    vanna
    0.42
    ाप्त
    0.42
     tear
    0.41
    apunov
    0.41
     const
    0.40
     san
    0.40
    sertation
    0.40
     Te
    0.39
    Activations Density 0.013%

    No Known Activations