© 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. 38892
    Prev
    Next
    INDEX
    Explanations

    printing

    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
     Efq
    -1.71
     Majefty
    -1.66
     printing
    -1.60
     Houſe
    -1.55
     Monfieur
    -1.52
     myſelf
    -1.45
     purpoſe
    -1.44
     printed
    -1.40
     poffible
    -1.34
     pleaſure
    -1.30
    POSITIVE LOGITS
    <eos>
    0.68
     (
    0.66
    !
    0.57
     in
    0.57
    ,
    0.56
    a
    0.55
     l
    0.55
     .
    0.55
     [
    0.54
    ↵
    0.52
    Activations Density 0.395%

    No Known Activations