© 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. 41491
    Prev
    Next
    INDEX
    Explanations

    R

    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
    R
    -1.50
     R
    -1.47
     r
    -0.77
    y
    -0.65
     la
    -0.63
    r
    -0.60
    P
    -0.56
     of
    -0.54
     P
    -0.53
    S
    -0.51
    POSITIVE LOGITS
     Monfieur
    1.34
     myſelf
    1.09
     Theſe
    1.04
     ſeveral
    1.03
     itſelf
    1.00
     themſelves
    0.96
    ſelves
    0.95
     faſt
    0.93
     $_"
    0.93
     Diſ
    0.92
    Activations Density 0.250%

    No Known Activations