© 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. 96380
    Prev
    Next
    INDEX
    Explanations

    completed

    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
     moindre
    -0.53
     typically
    -0.49
     للمعارف
    -0.48
     समीक्षाओं
    -0.48
    typically
    -0.47
    нибудь
    -0.47
    gantung
    -0.47
    Depending
    -0.47
     Depending
    -0.46
     tends
    -0.46
    POSITIVE LOGITS
    ISupport
    0.84
    MessageInfo
    0.65
    rouwen
    0.62
     utilisation
    0.62
     BorderRadius
    0.60
     BrowserModule
    0.59
     rss
    0.59
     dsl
    0.59
    $}}
    0.59
    XXV
    0.59
    Activations Density 0.001%

    No Known Activations