© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15255
    Prev
    Next
    INDEX
    Explanations

    so

    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
     propOrder
    -0.92
    Datuak
    -0.75
    AntiForgeryToken
    -0.71
    ConstraintMaker
    -0.71
     فريبيس
    -0.66
    MLLoader
    -0.65
     vastaan
    -0.63
    TagHelper
    -0.63
     kasarigan
    -0.62
     GenerationType
    -0.61
    POSITIVE LOGITS
    ,
    0.56
    ngOnInit
    0.49
     long
    0.48
     hot
    0.46
    (
    0.46
     magn
    0.45
     nocturnal
    0.45
     vip
    0.45
     amp
    0.44
     nuclei
    0.44
    Activations Density 0.007%

    No Known Activations