© 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. 0-CLT-HP
    7. 38745
    Prev
    Next
    INDEX
    Explanations

    accidents and dangerous situations

    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
     kasarigan
    -1.03
     متعلقه
    -1.02
     pleaſure
    -1.00
     تانيه
    -0.93
     purpoſe
    -0.90
     ſmall
    -0.88
     myſelf
    -0.88
     immersion
    -0.87
     Efq
    -0.86
     testify
    -0.86
    POSITIVE LOGITS
    er
    0.81
    ed
    0.76
    i
    0.69
    e
    0.68
    es
    0.67
    ist
    0.66
    .
    0.59
    -
    0.59
    ing
    0.57
    ,
    0.56
    Activations Density 0.046%

    No Known Activations