© 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. 5-CLT-HP
    7. 94124
    Prev
    Next
    INDEX
    Explanations

    ok

    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
    "}")
    -0.64
    FormTagHelper
    -0.62
     horrend
    -0.54
    UseVisualStyle
    -0.53
    ]--;
    -0.51
     propOrder
    -0.51
    TOS
    -0.50
     hôte
    -0.50
    rungsseite
    -0.49
    rtz
    -0.48
    POSITIVE LOGITS
     فريبيس
    0.59
    IsContent
    0.56
     незавершена
    0.54
    SharedDtor
    0.51
     linkovi
    0.51
    ish
    0.49
     Albe
    0.48
    TypedDataSet
    0.47
     DbSet
    0.46
    MENAFN
    0.46
    Activations Density 0.002%

    No Known Activations