© 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. 5-CLT-HP
    7. 93709
    Prev
    Next
    INDEX
    Explanations

    past time periods

    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
    SharedDtor
    -0.53
    oost
    -0.43
    …~
    -0.41
     betweenstory
    -0.39
    containsKey
    -0.39
    terly
    -0.39
     presents
    -0.38
    wasi
    -0.38
    LabelTagHelper
    -0.37
    leyebilirsiniz
    -0.37
    POSITIVE LOGITS
    Espèce
    0.96
     يتيمه
    0.75
    ftagPool
    0.72
    MIDDLEWARE
    0.71
    hoeddwyd
    0.67
     defaultstate
    0.66
    ClientRect
    0.63
     Roskov
    0.63
    autorest
    0.63
    ieR
    0.62
    Activations Density 0.001%

    No Known Activations