© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93245
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    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
     (
    -1.48
     "
    -1.32
     “
    -1.24
     
    -1.05
     '
    -1.01
    ↵↵
    -1.00
    <eos>
    -0.99
     [
    -0.96
     I
    -0.93
     A
    -0.93
    POSITIVE LOGITS
     itſelf
    1.63
     myſelf
    1.60
     auffi
    1.51
     purpoſe
    1.49
     Monfieur
    1.48
     ainfi
    1.46
     avoient
    1.45
     étoient
    1.44
     Efq
    1.44
     pleaſure
    1.42
    Activations Density 0.214%

    No Known Activations