© 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. 15240
    Prev
    Next
    INDEX
    Explanations

    as

    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
    Personensuche
    -0.79
    ConstraintMaker
    -0.70
     ujednoznacz
    -0.67
     Reverso
    -0.65
    StoryboardSegue
    -0.64
    Datuak
    -0.63
     AllMovie
    -0.60
    AddTagHelper
    -0.60
    RenderAtEndOf
    -0.60
    存于互联网档案馆
    -0.59
    POSITIVE LOGITS
    NonNull
    0.57
     phag
    0.48
     называют
    0.47
     thermocouple
    0.45
     lobe
    0.43
    InstrumentedTest
    0.43
     &$
    0.43
    IsPostBack
    0.42
     and
    0.41
     Ever
    0.40
    Activations Density 0.008%

    No Known Activations