© 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. 5-CLT-HP
    7. 3710
    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
    DockStyle
    -0.89
     AssemblyCulture
    -0.82
    Хьажоргаш
    -0.73
     يتيمه
    -0.71
     للاسماء
    -0.66
    GraphicsUnit
    -0.65
    writeFieldEnd
    -0.63
    IsMutable
    -0.63
     الحره
    -0.60
    ViewFeatures
    -0.59
    POSITIVE LOGITS
    #+#
    0.60
     drivers
    0.42
    Meik
    0.41
     traffic
    0.41
    toppers
    0.40
    locationManager
    0.40
     Jerman
    0.39
     security
    0.39
     Sush
    0.39
    fromLTRB
    0.39
    Activations Density 0.001%

    No Known Activations