© 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. 0-CLT-HP
    7. 41153
    Prev
    Next
    INDEX
    Explanations

    what

    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
    NOW
    -0.71
     scolaires
    -0.66
     européennes
    -0.62
     Paglinawan
    -0.60
    OK
    -0.59
     normaux
    -0.58
     supérieures
    -0.57
     quæ
    -0.57
     commerciales
    -0.56
     literario
    -0.55
    POSITIVE LOGITS
    adays
    1.05
     kasarigan
    0.73
    ASHI
    0.73
    antMatchers
    0.72
    ympto
    0.71
    μβρίου
    0.71
    entown
    0.68
    sions
    0.68
    nastics
    0.68
    sterious
    0.68
    Activations Density 1.605%

    No Known Activations