© 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. 5-CLT-HP
    7. 98143
    Prev
    Next
    INDEX
    Explanations

    recent

    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
    存于互联网档案馆
    -1.06
    ſelf
    -1.01
    ſelves
    -0.96
    ंदीखरीदारी
    -0.96
     Efq
    -0.92
     ſtate
    -0.91
     myſelf
    -0.91
     preſent
    -0.90
     itſelf
    -0.90
    Datuak
    -0.88
    POSITIVE LOGITS
     and
    0.68
     past
    0.57
     but
    0.53
     recent
    0.51
     anda
    0.51
    ,
    0.49
     popular
    0.49
     astounding
    0.48
     as
    0.47
     historic
    0.46
    Activations Density 0.004%

    No Known Activations