© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1314
    Prev
    Next
    INDEX
    Explanations

    Stop

    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
    Stop
    -1.20
     Stop
    -1.20
     STOP
    -0.88
    STOP
    -0.88
    stop
    -0.60
     stop
    -0.54
    Close
    -0.50
    पया
    -0.50
    casi
    -0.45
    OUT
    -0.45
    POSITIVE LOGITS
    ScopeManager
    0.84
     Monfieur
    0.81
     igång
    0.79
     Anſ
    0.76
    ModelSerializer
    0.76
     houſe
    0.75
     Majefty
    0.75
    +#+#
    0.74
     myſelf
    0.72
     ſmall
    0.71
    Activations Density 1.729%

    No Known Activations