© 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. 706
    Prev
    Next
    INDEX
    Explanations

    :

    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
     Италијани
    -0.91
    awtextra
    -0.81
    bootstrapcdn
    -0.75
    GEBURTSDATUM
    -0.72
     esternos
    -0.66
    ьаж
    -0.66
     CreateTagHelper
    -0.65
    IntoConstraints
    -0.64
    UrlResolution
    -0.63
    mobileqq
    -0.62
    POSITIVE LOGITS
    VisualStudio
    0.45
    DropTable
    0.44
     Randall
    0.43
    ract
    0.41
     Mathematica
    0.39
     promul
    0.39
    andal
    0.37
    SetTitle
    0.36
    Xna
    0.36
     Sulphur
    0.36
    Activations Density 0.014%

    No Known Activations