© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 5023
    Prev
    Next
    INDEX
    Explanations

    coding and names

    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
    WriteBarrier
    -0.59
     pro
    -0.58
    Referanser
    -0.51
     تضيفلها
    -0.50
    LLOW
    -0.50
    formKey
    -0.48
    pro
    -0.48
    коменду
    -0.48
     <=",
    -0.47
     sal
    -0.47
    POSITIVE LOGITS
     depoz
    0.57
    principalTable
    0.54
     défin
    0.52
     giuri
    0.52
     indefinitely
    0.52
     rapporti
    0.52
     indefinite
    0.51
     énergé
    0.51
    dată
    0.50
    hdessä
    0.50
    Activations Density 0.006%

    No Known Activations