Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44395
    Prev
    Next
    INDEX
    Explanations

    Cour

    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
     pic
    -0.69
     free
    -0.63
     Buch
    -0.62
     et
    -0.59
     book
    -0.58
     Book
    -0.57
     est
    -0.56
     Pic
    -0.55
     h
    -0.55
     av
    -0.54
    POSITIVE LOGITS
     feroit
    0.86
     énergé
    0.85
    AndEndTag
    0.81
     étoient
    0.79
     pouvoit
    0.79
     vectorielles
    0.78
     ainfi
    0.77
     auroit
    0.77
     démocr
    0.76
     regeringen
    0.75
    Activations Density 0.228%

    No Known Activations