© 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. 97630
    Prev
    Next
    INDEX
    Explanations

    biographical information

    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
    SharedDtor
    -0.78
     resourceCulture
    -0.77
     <=",
    -0.70
    Билгалдахарш
    -0.67
     JpaRepository
    -0.66
    principalTable
    -0.65
    principalColumn
    -0.65
     CreateTagHelper
    -0.64
    IntoConstraints
    -0.62
    tagext
    -0.59
    POSITIVE LOGITS
    UIManager
    0.45
     SwitchCompat
    0.45
     shippers
    0.44
    CppCodeGen
    0.44
    forRoot
    0.43
    wanza
    0.42
     aryl
    0.42
    cyc
    0.42
    AsyncResult
    0.42
     Organizador
    0.41
    Activations Density 0.002%

    No Known Activations