© 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. 44224
    Prev
    Next
    INDEX
    Explanations

    Mathematics

    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
     Majefty
    -1.50
     mathematics
    -1.49
     mathematicians
    -1.48
     Monfieur
    -1.47
     mathematician
    -1.45
     myſelf
    -1.43
     houſe
    -1.39
     Normdatei
    -1.38
     Efq
    -1.38
     Houſe
    -1.36
    POSITIVE LOGITS
    .
    0.70
     in
    0.69
     (
    0.69
    ,
    0.68
     
    0.63
     is
    0.59
     of
    0.58
     per
    0.57
     for
    0.57
     "
    0.57
    Activations Density 0.292%

    No Known Activations