© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1642
    Prev
    Next
    INDEX
    Explanations

    of

    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
    PhysRev
    -0.66
     useRouter
    -0.57
    wahati
    -0.57
    assertRaises
    -0.54
    RenderAtEndOf
    -0.53
    abstractmethod
    -0.53
    apimachinery
    -0.53
    HtmlAttribute
    -0.52
    Obras
    -0.51
     BaseActivity
    -0.51
    POSITIVE LOGITS
     '\\;'
    0.60
     protoimpl
    0.59
    AddTagHelper
    0.57
    Legături
    0.50
    Спољашње
    0.47
    <bos>
    0.47
    Enllaços
    0.47
    のである
    0.46
    voit
    0.44
     Wissens
    0.44
    Activations Density 0.001%

    No Known Activations