© 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. 72154
    Prev
    Next
    INDEX
    Explanations

    semiconductor

    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
     виправивши
    -0.81
    tagHelperRunner
    -0.63
    Kontrola
    -0.61
    contentLoaded
    -0.61
    GEBURTSDATUM
    -0.58
    parsedMessage
    -0.57
     متعلقه
    -0.57
    RenderAtEndOf
    -0.52
    ItemBackground
    -0.52
     CreateTagHelper
    -0.51
    POSITIVE LOGITS
    xfer
    0.57
    uksessa
    0.52
     vibrate
    0.50
    csname
    0.49
    वरण
    0.48
    boldmath
    0.47
     gradova
    0.46
    ELDS
    0.45
    modities
    0.45
    ).
    0.44
    Activations Density 0.001%

    No Known Activations