© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96999
    Prev
    Next
    INDEX
    Explanations

    reporting/articles

    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
     defaultstate
    -0.65
    Попис
    -0.48
     unknownFields
    -0.45
     Paglinawan
    -0.43
     Италијани
    -0.41
    Bakgrunnsstoff
    -0.41
    atalos
    -0.39
    ⓘ
    -0.38
    いずれ
    -0.38
    ますが
    -0.37
    POSITIVE LOGITS
    AddTagHelper
    0.65
    PullParser
    0.62
    TagMode
    0.62
    BagLayout
    0.61
     ReactDOM
    0.61
     Eup
    0.60
    RetentionPolicy
    0.60
     bezeichneter
    0.59
    UrlResolution
    0.59
    IFICATE
    0.58
    Activations Density 0.000%

    No Known Activations