© 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. 1879
    Prev
    Next
    INDEX
    Explanations

    testis

    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
    Chham
    -0.56
    tinyos
    -0.52
    ắn
    -0.52
    SequentialGroup
    -0.50
     متعلقه
    -0.48
     count
    -0.47
    ToMany
    -0.47
    TagHelper
    -0.47
     namen
    -0.46
    olingo
    -0.46
    POSITIVE LOGITS
    IUrlHelper
    0.57
     laikā
    0.54
     triglycerides
    0.53
    ſelf
    0.53
     hoeft
    0.52
    angliski
    0.49
     itſelf
    0.49
     Jefus
    0.48
     thermoc
    0.48
    +:+
    0.48
    Activations Density 0.002%

    No Known Activations