© 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. 2092
    Prev
    Next
    INDEX
    Explanations

    task/goal

    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
    غم
    -0.45
    richTextPanel
    -0.42
     as
    -0.42
     mini
    -0.42
    奇
    -0.40
     Prinz
    -0.39
    ColumnHeaders
    -0.38
    vtx
    -0.37
     Rar
    -0.35
    ɵɵelementStart
    -0.35
    POSITIVE LOGITS
     تضيفلها
    0.77
    tagHelperRunner
    0.77
    Personendaten
    0.76
    RenderAtEndOf
    0.76
    AsUp
    0.76
     dAtA
    0.70
    HasOne
    0.69
    OGND
    0.68
    مصادر
    0.68
    脚注の使い方
    0.66
    Activations Density 0.004%

    No Known Activations