© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3456
    Prev
    Next
    INDEX
    Explanations

    that

    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
     had
    -0.58
     propOrder
    -0.57
     genoux
    -0.56
     répondu
    -0.56
     Factbook
    -0.55
     cancelamento
    -0.52
    IUrlHelper
    -0.52
     was
    -0.52
    hintText
    -0.51
     folgte
    -0.51
    POSITIVE LOGITS
     the
    0.74
     a
    0.62
    webElement
    0.60
     an
    0.58
     all
    0.57
     htons
    0.56
     certain
    0.56
    }^{+}$
    0.54
     such
    0.54
     something
    0.53
    Activations Density 0.002%

    No Known Activations