© 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. 0-CLT-HP
    7. 41107
    Prev
    Next
    INDEX
    Explanations

    Neu

    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
    iel
    -0.74
    neu
    -0.62
    threatening
    -0.61
     Retina
    -0.52
    綜合報導
    -0.51
    c
    -0.50
     surla
    -0.50
     siyang
    -0.48
    afficheront
    -0.47
     Usher
    -0.47
    POSITIVE LOGITS
    brainly
    0.63
    ebvre
    0.60
    водства
    0.57
     Duro
    0.56
    ướ
    0.56
     Enrollment
    0.56
    ChildScrollView
    0.54
     sherds
    0.54
    lgari
    0.54
    endung
    0.53
    Activations Density 1.200%

    No Known Activations