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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12922
    Prev
    Next
    INDEX
    Explanations

    our

    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
     nation
    -0.80
     nación
    -0.76
     Nation
    -0.57
    nation
    -0.56
     États
    -0.56
     NATION
    -0.52
    ก่
    -0.52
     américa
    -0.49
    Nation
    -0.47
    lə
    -0.47
    POSITIVE LOGITS
     bezeichneter
    0.78
    ValueStyle
    0.78
    AndEndTag
    0.77
    CreateModel
    0.72
    StoryboardSegue
    0.71
    Carriera
    0.71
     utafitiHapana
    0.68
     cherchés
    0.66
    ⎩
    0.65
    abestanden
    0.65
    Activations Density 0.021%

    No Known Activations