© 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. 0-CLT-HP
    7. 95261
    Prev
    Next
    INDEX
    Explanations

    secondary

    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
     secondary
    -2.45
    secondary
    -2.25
     Secondary
    -2.09
    Secondary
    -2.06
     SECONDARY
    -1.74
    SECONDARY
    -1.70
     secondaire
    -1.58
     beans
    -1.47
     secondaires
    -1.34
     secundaria
    -1.32
    POSITIVE LOGITS
    ly
    0.58
    AnchorTagHelper
    0.54
     BnF
    0.53
    HtmlAttribute
    0.52
    Портал
    0.51
    ))/(
    0.51
     bulle
    0.49
    NameInMap
    0.49
     automaton
    0.49
    asgi
    0.49
    Activations Density 0.284%

    No Known Activations