© 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. 3083
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    <bos>
    -0.87
    LookAnd
    -0.59
    tagHelperRunner
    -0.59
     للاسماء
    -0.56
    hyrchwyd
    -0.52
    كتشاف
    -0.51
    BarStyle
    -0.47
    طلحات
    -0.47
    fillType
    -0.47
    InjectAttribute
    -0.47
    POSITIVE LOGITS
     BorderSide
    0.61
    脚注の使い方
    0.61
     ReactDOM
    0.60
     eventdata
    0.56
    Referències
    0.55
     transfieras
    0.54
    setLayoutManager
    0.53
    TagMode
    0.53
    makeText
    0.53
    קישורים
    0.52
    Activations Density 0.045%

    No Known Activations