© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73112
    Prev
    Next
    INDEX
    Explanations

    various text snippets

    np_max-act-logits · 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
     Gadget
    -0.54
    ATRE
    -0.52
     Device
    -0.51
     cí
    -0.51
     DEVICE
    -0.50
     Fixture
    -0.50
     précie
    -0.49
    fare
    -0.49
     mueble
    -0.48
    ValueStyle
    -0.47
    POSITIVE LOGITS
    LookAnd
    0.69
     manip
    0.68
     props
    0.63
     tongs
    0.61
     trays
    0.57
     parach
    0.56
     scarves
    0.54
     shaving
    0.54
     scissors
    0.53
    initializeApp
    0.53
    Activations Density 0.001%

    No Known Activations