© 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. 1-CLT-HP
    7. 13279
    Prev
    Next
    INDEX
    Explanations

    technical writing and programming

    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
    ########.
    -0.68
    enderror
    -0.68
     transfieras
    -0.62
    BeginInit
    -0.59
    EndInit
    -0.58
     clarity
    -0.53
    aratus
    -0.53
    arote
    -0.53
    SuspendLayout
    -0.53
    lequin
    -0.52
    POSITIVE LOGITS
    .*")]
    0.66
     NOI
    0.59
     оригіналу
    0.58
     forState
    0.55
     تانيه
    0.52
    ãe
    0.49
     consultato
    0.48
    richTextPanel
    0.46
     '{@
    0.46
    </s>
    0.46
    Activations Density 0.115%

    No Known Activations