© 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. 4-CLT-HP
    7. 2106
    Prev
    Next
    INDEX
    Explanations

    in

    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
     quelcon
    -0.46
    BrowserModule
    -0.46
    AutoresizingMask
    -0.46
     NgModule
    -0.45
    equ
    -0.41
    LayoutConstraint
    -0.40
    RunWith
    -0.40
     Pote
    -0.38
    一段
    -0.37
     Monta
    -0.37
    POSITIVE LOGITS
    transQ
    0.77
    oa̍t
    0.74
     يتيمه
    0.71
    Tembelea
    0.70
    بوابة
    0.69
     Italijani
    0.67
     linkovi
    0.66
    المكان
    0.65
    رشف
    0.65
     ddelweddau
    0.64
    Activations Density 0.016%

    No Known Activations