© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3403
    Prev
    Next
    INDEX
    Explanations

    that

    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
     Instead
    -0.61
    让我们
    -0.51
     Although
    -0.50
     Each
    -0.49
    ,
    -0.49
     Later
    -0.48
     Your
    -0.48
     We
    -0.48
    Instead
    -0.48
     Anyone
    -0.47
    POSITIVE LOGITS
    <bos>
    0.85
    تقاوى
    0.77
    StructEnd
    0.75
    AndEndTag
    0.72
    LabelTagHelper
    0.69
     propOrder
    0.68
    SharedCtor
    0.66
    SharedDtor
    0.66
     Reverso
    0.65
     Jefus
    0.65
    Activations Density 0.002%

    No Known Activations