© 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. 1-CLT-HP
    7. 13275
    Prev
    Next
    INDEX
    Explanations

    ographs

    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
     Pallas
    -1.25
     CreateTagHelper
    -0.74
     متعلقه
    -0.68
    loon
    -0.63
    PositiveButton
    -0.59
    Jereo
    -0.59
    ("'"
    -0.59
    קישורים
    -0.57
    ingly
    -0.57
    __(/*!
    -0.56
    POSITIVE LOGITS
     arşivlendi
    0.69
    IRED
    0.55
    ima
    0.54
    ite
    0.51
    Tear
    0.50
    viewBox
    0.49
     Tear
    0.48
    معلومات
    0.48
     Atem
    0.48
    imų
    0.47
    Activations Density 0.006%

    No Known Activations