© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 93983
    Prev
    Next
    INDEX
    Explanations

    when

    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
     and
    -0.58
     than
    -0.57
     andar
    -0.54
    tvguidetime
    -0.52
    utilisons
    -0.52
    ьогодні
    -0.52
    bcryptjs
    -0.51
    Give
    -0.50
    bewerken
    -0.49
     aujourd
    -0.48
    POSITIVE LOGITS
     it
    0.64
     désolés
    0.59
     done
    0.59
    Varios
    0.58
     several
    0.55
    onViewCreated
    0.55
    IsContent
    0.54
     there
    0.52
    titleMargin
    0.52
     many
    0.51
    Activations Density 0.001%

    No Known Activations