© 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. 38708
    Prev
    Next
    INDEX
    Explanations

    code and data structures

    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
     screen
    -0.69
    screen
    -0.69
    protoimpl
    -0.66
     Screen
    -0.61
     SCREEN
    -0.61
     continúas
    -0.60
    Източници
    -0.59
    ElementException
    -0.59
    creen
    -0.58
    Screen
    -0.58
    POSITIVE LOGITS
     nakalista
    0.55
     Amon
    0.53
    ramid
    0.51
    shadowRadius
    0.50
     assassination
    0.50
    asgi
    0.49
     civile
    0.48
     apostles
    0.48
     RestTemplate
    0.47
     całym
    0.47
    Activations Density 0.158%

    No Known Activations