© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9651
    Prev
    Next
    INDEX
    Explanations

    associate

    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
    din
    -0.45
    down
    -0.45
    jec
    -0.43
    rea
    -0.42
    mstyle
    -0.41
     /
    -0.41
     Nutz
    -0.40
    estad
    -0.40
    s
    -0.40
    linear
    -0.40
    POSITIVE LOGITS
     myſelf
    0.96
     itſelf
    0.85
     Monfieur
    0.83
     ſeveral
    0.82
     étoient
    0.80
     cdti
    0.79
     whoſe
    0.78
     themſelves
    0.77
     Efq
    0.76
     iſt
    0.75
    Activations Density 0.012%

    No Known Activations