© 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. 5-CLT-HP
    7. 2103
    Prev
    Next
    INDEX
    Explanations

    Negations

    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
    ///</
    -0.65
     estekak
    -0.58
    TagMode
    -0.56
     }^{[
    -0.55
     Distributed
    -0.53
     defaultstate
    -0.51
    Distributed
    -0.50
     aDecoder
    -0.49
     rękaw
    -0.48
     diyor
    -0.48
    POSITIVE LOGITS
    +#+#
    0.58
     ModelExpression
    0.57
     FishBase
    0.56
     measurements
    0.56
     exact
    0.55
    toria
    0.54
    ört
    0.52
    znam
    0.52
    出版年
    0.52
     Exact
    0.52
    Activations Density 0.004%

    No Known Activations