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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4520
    Prev
    Next
    INDEX
    Explanations

    saving/rescuing

    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
    henswürdigkeiten
    -0.50
    abetes
    -0.45
    }}],
    -0.42
    racuse
    -0.42
    entee
    -0.41
    NAF
    -0.41
    detto
    -0.41
     myeloma
    -0.41
     Yer
    -0.40
    textTheme
    -0.40
    POSITIVE LOGITS
     '\\;'
    0.78
     life
    0.66
    Personendaten
    0.64
     ProtoMessage
    0.62
    WebVitals
    0.61
     оригіналу
    0.60
    HttpServlet
    0.60
    ьаж
    0.57
    exitRule
    0.57
    apimachinery
    0.56
    Activations Density 0.004%

    No Known Activations