© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4701
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    AndEndTag
    -0.79
     مشين
    -0.78
     الحره
    -0.78
     متعلقه
    -0.76
     CreateTagHelper
    -0.73
    AddTagHelper
    -0.70
    UrlResolution
    -0.69
    MessageOf
    -0.69
    ."));
    -0.69
    StoryboardSegue
    -0.69
    POSITIVE LOGITS
     spéciaux
    0.45
     daß
    0.45
    ponses
    0.43
     malades
    0.43
     asemenea
    0.43
    essentiel
    0.42
     conseguenza
    0.41
     ontem
    0.40
     antigos
    0.40
     piemē
    0.40
    Activations Density 0.014%

    No Known Activations