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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96414
    Prev
    Next
    INDEX
    Explanations

    varied internet topics

    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
    providedIn
    -0.84
    LookAnd
    -0.80
    出版年
    -0.74
    IntoConstraints
    -0.73
     CreateTagHelper
    -0.71
    endphp
    -0.69
    ConfigureAwait
    -0.68
     JSTOR
    -0.67
    URLException
    -0.67
    featureID
    -0.67
    POSITIVE LOGITS
     is
    1.00
     can
    0.96
     are
    0.86
     would
    0.79
     will
    0.78
     has
    0.77
     were
    0.74
     was
    0.73
     should
    0.71
     may
    0.70
    Activations Density 0.026%

    No Known Activations