© 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. 943
    Prev
    Next
    INDEX
    Explanations

    legal/business documents

    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
     myſelf
    -0.85
    ParallelGroup
    -0.84
     snippetHide
    -0.81
    AddTagHelper
    -0.81
    SharedDtor
    -0.74
    ंदीखरीदारी
    -0.74
     ―――――
    -0.72
    Tembelea
    -0.72
     Jefus
    -0.71
    '}>
    -0.71
    POSITIVE LOGITS
     (
    0.60
     "
    0.53
    Kapcsolódó
    0.50
     “
    0.49
     or
    0.49
    /
    0.48
     /
    0.47
    ,
    0.47
    and
    0.46
    <eos>
    0.46
    Activations Density 0.301%

    No Known Activations