© 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. 0-CLT-HP
    7. 42316
    Prev
    Next
    INDEX
    Explanations

    bas

    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
     base
    -1.55
     Base
    -1.52
    base
    -1.39
    Base
    -1.37
     BASE
    -1.30
     bas
    -1.27
     baseline
    -1.21
    BASE
    -1.20
    baseline
    -1.15
     basal
    -1.14
    POSITIVE LOGITS
     تضيفلها
    0.55
    SizeF
    0.55
     Stag
    0.54
    SizeMode
    0.54
    ]),
    0.51
     CreateTagHelper
    0.51
    oform
    0.50
    Revenir
    0.50
    RectangleBorder
    0.49
    quine
    0.48
    Activations Density 1.508%

    No Known Activations