Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45513
    Prev
    Next
    INDEX
    Explanations

    on

    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
    AndEndTag
    -0.77
     continúas
    -0.65
    chtigkeit
    -0.61
    (___
    -0.61
    WriteTagHelper
    -0.57
    qrstuvwxyz
    -0.57
    oader
    -0.57
    chmal
    -0.57
    ViewFeatures
    -0.57
    
    -0.57
    POSITIVE LOGITS
    findpost
    0.52
    set
    0.50
     <>",
    0.44
     pregnant
    0.44
     blood
    0.44
     cancer
    0.42
    jectable
    0.42
     asleep
    0.42
    esthes
    0.42
     pills
    0.40
    Activations Density 0.031%

    No Known Activations