© 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. 0-CLT-HP
    7. 40517
    Prev
    Next
    INDEX
    Explanations

    travel

    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
    fortawesome
    -0.65
     We
    -0.54
     departament
    -0.43
    naeus
    -0.42
     I
    -0.41
    Hentet
    -0.40
     régions
    -0.40
     idéia
    -0.40
     
    -0.40
     my
    -0.40
    POSITIVE LOGITS
    Tikang
    0.82
    <bos>
    0.77
     Shakspeare
    0.74
    hyrchwyd
    0.69
     jsPsych
    0.68
     doubtnut
    0.68
    はじめに
    0.66
     crib
    0.66
     DBNull
    0.66
    verwijspagina
    0.65
    Activations Density 0.128%

    No Known Activations