© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13742
    Prev
    Next
    INDEX
    Explanations

    research

    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
    
    -0.65
     الحره
    -0.64
     RequestMethod
    -0.58
    sont
    -0.56
     समीक्षाओं
    -0.56
    Vidite
    -0.55
    ]")]
    -0.53
    Lähteet
    -0.52
     Ocean
    -0.52
     ride
    -0.50
    POSITIVE LOGITS
    WriteTagHelper
    0.63
    way
    0.63
    plate
    0.57
    grounds
    0.54
    ioutil
    0.53
    ways
    0.52
    guards
    0.51
    bestos
    0.50
    tags
    0.49
    card
    0.48
    Activations Density 0.012%

    No Known Activations