© 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. 4-CLT-HP
    7. 1684
    Prev
    Next
    INDEX
    Explanations

    technology

    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
     يتيمه
    -0.96
    IUrlHelper
    -0.74
    OGND
    -0.74
    MessageTagHelper
    -0.74
    IntoConstraints
    -0.73
     useDispatch
    -0.73
     StatefulWidget
    -0.73
    WriteLiteral
    -0.71
     wired
    -0.70
     CommonModule
    -0.70
    POSITIVE LOGITS
    tok
    0.52
    dan
    0.52
    up
    0.45
     Dan
    0.42
    {$
    0.41
    uo
    0.41
    ato
    0.40
    Dan
    0.40
    сій
    0.40
    ృ
    0.40
    Activations Density 0.006%

    No Known Activations