© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96628
    Prev
    Next
    INDEX
    Explanations

    state abbreviations

    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
    posedge
    -0.75
    queryInterface
    -0.70
    LookAnd
    -0.69
    EndProject
    -0.64
    ⓧ
    -0.63
    HasBeenSet
    -0.63
    Enllaces
    -0.61
     متعلقه
    -0.61
    ագրություններ
    -0.60
    Tembelea
    -0.60
    POSITIVE LOGITS
     
    0.52
    Dettagli
    0.48
    */;
    0.43
     considérons
    0.42
    umentos
    0.41
     zul
    0.40
    клопе
    0.40
    giene
    0.40
     United
    0.40
     meines
    0.39
    Activations Density 0.014%

    No Known Activations