© 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. 40636
    Prev
    Next
    INDEX
    Explanations

    turret

    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
     emergency
    -0.81
    EDEFAULT
    -0.81
    IntoConstraints
    -0.73
     &___
    -0.70
     étoient
    -0.69
    Emergency
    -0.69
     enfans
    -0.69
     âmes
    -0.68
    emergency
    -0.67
     avoient
    -0.66
    POSITIVE LOGITS
    s
    0.78
     trails
    0.58
     int
    0.52
     Int
    0.51
    san
    0.50
    ся
    0.50
     indo
    0.50
     gain
    0.49
     trials
    0.48
    året
    0.48
    Activations Density 0.051%

    No Known Activations