© 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. 1993
    Prev
    Next
    INDEX
    Explanations

    meyer

    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
     Dogs
    -1.10
     dogs
    -0.98
     DOGS
    -0.92
    dogs
    -0.86
     Hills
    -0.83
    Dogs
    -0.81
    Hills
    -0.74
     dog
    -0.74
     مرئيه
    -0.74
     HILLS
    -0.71
    POSITIVE LOGITS
    ism
    0.52
     préf
    0.52
     préfé
    0.50
    KommentareTeilen
    0.50
    elaar
    0.48
    weich
    0.47
    readystatechange
    0.45
    erenc
    0.44
    ftagPool
    0.44
    UnusedPrivate
    0.43
    Activations Density 0.810%

    No Known Activations