© 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. 0-CLT-HP
    4. 1050
    Prev
    Next
    INDEX
    Explanations

    reduction

    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
     reduction
    -1.32
     myſelf
    -0.89
     Reduction
    -0.88
    reduction
    -0.87
     REDUCTION
    -0.87
     Theſe
    -0.83
     reductions
    -0.82
     houſe
    -0.82
     themſelves
    -0.81
     Efq
    -0.79
    POSITIVE LOGITS
     оригіналу
    0.50
     Bourgoin
    0.50
    Guest
    0.47
    omyces
    0.47
    ger
    0.47
    o
    0.46
    но
    0.45
    circled
    0.44
    do
    0.44
    Kariera
    0.44
    Activations Density 0.052%

    No Known Activations