© 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. 3234
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ting
    -0.63
     other
    -0.55
    viewBox
    -0.54
    viewpager
    -0.54
    ,
    -0.52
     
    -0.52
    úcar
    -0.50
     of
    -0.50
     (
    -0.47
    tingen
    -0.47
    POSITIVE LOGITS
    DockStyle
    0.82
     متعلقه
    0.70
    AsUp
    0.68
    rungsseite
    0.68
    脚注の使い方
    0.67
     Roskov
    0.67
    SBATCH
    0.66
    ьаж
    0.65
     enfans
    0.65
    ValueStyle
    0.64
    Activations Density 0.004%

    No Known Activations