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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 972
    Prev
    Next
    INDEX
    Explanations

    ambassador

    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
     camera
    -1.05
     Camera
    -1.01
     cam
    -0.99
     Cam
    -0.99
    cam
    -0.96
    Cam
    -0.96
    CAM
    -0.92
    Camera
    -0.91
    camera
    -0.86
     CAM
    -0.86
    POSITIVE LOGITS
    日閲覧
    0.59
    AndEndTag
    0.57
     Vitae
    0.57
    Mace
    0.52
    literals
    0.48
    ISupport
    0.48
     Astrophysics
    0.46
     }{@
    0.45
    equalTo
    0.45
     poda
    0.45
    Activations Density 0.071%

    No Known Activations