© 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. 39996
    Prev
    Next
    INDEX
    Explanations

    solar and purple

    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
     ſmall
    -1.16
     Majefty
    -1.05
     pleaſure
    -1.05
     themſelves
    -1.03
     ſeveral
    -1.03
     Efq
    -1.03
     himſelf
    -1.02
     Monfieur
    -0.99
     uſed
    -0.99
     myſelf
    -0.98
    POSITIVE LOGITS
    er
    0.77
    es
    0.73
    s
    0.71
    o
    0.66
    ↵
    0.65
    ↵↵
    0.64
    os
    0.64
    <eos>
    0.60
    the
    0.58
     K
    0.57
    Activations Density 0.029%

    No Known Activations