Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12686
    Prev
    Next
    INDEX
    Explanations

    network sockets

    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
     prêtres
    -0.57
     fourrure
    -0.56
     regionales
    -0.56
     igång
    -0.53
     complètes
    -0.51
     médicaux
    -0.51
     achet
    -0.51
     dieux
    -0.50
     sabbia
    -0.50
     vectorielles
    -0.49
    POSITIVE LOGITS
    AndEndTag
    0.84
    RenderAtEndOf
    0.71
    ardless
    0.64
     فريبيس
    0.59
    UnusedPrivate
    0.59
    abestanden
    0.59
    WithIOException
    0.58
     resourceCulture
    0.58
     defaultstate
    0.57
    IntoConstraints
    0.57
    Activations Density 0.028%

    No Known Activations