© 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. 72472
    Prev
    Next
    INDEX
    Explanations

    mixed textual content

    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
     own
    -2.09
     Own
    -1.70
    Own
    -1.62
    own
    -1.60
     eigene
    -1.56
     eigenen
    -1.53
    自己的
    -1.48
     eigenes
    -1.48
     eigener
    -1.47
     OWN
    -1.45
    POSITIVE LOGITS
    Tikang
    0.72
    yntaxException
    0.66
     in
    0.61
    DeleteBehavior
    0.61
    GraphicsUnit
    0.60
    TagMode
    0.59
    arial
    0.58
    URLException
    0.57
    ManagedBean
    0.56
     createState
    0.54
    Activations Density 0.001%

    No Known Activations