© 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. 97753
    Prev
    Next
    INDEX
    Explanations

    Code and programming contexts

    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
     F
    -0.57
     de
    -0.51
     S
    -0.50
     f
    -0.49
    .
    -0.49
     P
    -0.49
     H
    -0.48
     D
    -0.47
    F
    -0.47
     d
    -0.46
    POSITIVE LOGITS
    MigrationBuilder
    0.98
     CreateTagHelper
    0.98
     Савезне
    0.87
    TagMode
    0.86
     feroit
    0.85
     itſelf
    0.84
     varandra
    0.83
    verwijspagina
    0.83
    ſelves
    0.82
     démocr
    0.81
    Activations Density 0.004%

    No Known Activations