© 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. 91439
    Prev
    Next
    INDEX
    Explanations

    either/or or comparison

    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
     jScrollPane
    -0.71
    ponses
    -0.66
    FilterChain
    -0.66
     BorderSide
    -0.65
    Hozzáférés
    -0.64
    tagHelperRunner
    -0.60
    δος
    -0.60
     party
    -0.60
    setContentView
    -0.59
    MIDDLEWARE
    -0.59
    POSITIVE LOGITS
     cœurs
    0.41
     strani
    0.41
     especiais
    0.40
     financieros
    0.39
    ContentAsync
    0.38
     kär
    0.38
     verantwoorde
    0.38
     šķ
    0.38
    tagext
    0.38
     conçus
    0.38
    Activations Density 0.001%

    No Known Activations