© 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. 96194
    Prev
    Next
    INDEX
    Explanations

    confidence

    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
     Theſe
    -0.59
    下载附件
    -0.59
    ſelves
    -0.59
    ruiter
    -0.57
     itſelf
    -0.56
    Становништво
    -0.55
     Marca
    -0.53
    quiel
    -0.52
    hidupan
    -0.52
     Jefus
    -0.52
    POSITIVE LOGITS
     kasarigan
    0.77
    MigrationBuilder
    0.76
     فريبيس
    0.62
    GEBURTSDATUM
    0.60
     noDo
    0.59
    يكب
    0.58
     Италијани
    0.58
     вікі
    0.57
    Välislingid
    0.57
     motion
    0.57
    Activations Density 0.001%

    No Known Activations