© 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. 1172
    Prev
    Next
    INDEX
    Explanations

    Adding

    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
     adding
    -2.36
    adding
    -2.13
    Adding
    -2.06
     Adding
    -2.06
     adds
    -1.48
     Adds
    -1.36
    adds
    -1.33
    Adds
    -1.28
     ajout
    -1.21
    ADDING
    -1.21
    POSITIVE LOGITS
     Paglinawan
    0.71
     CreateTagHelper
    0.70
    ContentAsync
    0.66
    Datuak
    0.65
    :✨
    0.64
    SourceChecksum
    0.64
    parsedMessage
    0.64
    GOTREF
    0.63
    Personensuche
    0.63
    JspWriter
    0.61
    Activations Density 0.204%

    No Known Activations