© 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. 3276
    Prev
    Next
    INDEX
    Explanations

    Politics/News

    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
    tagHelperRunner
    -0.79
    +#+#
    -0.64
     Mahmoud
    -0.64
    queryInterface
    -0.56
    FontStyle
    -0.56
    出版年
    -0.55
     Վերցված
    -0.53
    cię
    -0.53
    FontOfSize
    -0.52
    Moral
    -0.52
    POSITIVE LOGITS
    RenderAtEndOf
    0.57
    Chham
    0.51
    Parcelize
    0.47
    ιβ
    0.46
    GOTREF
    0.45
     ostavi
    0.45
    참고
    0.44
     Rigidbody
    0.44
    subprocess
    0.44
     glab
    0.44
    Activations Density 0.000%

    No Known Activations