© 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. 5-CLT-HP
    7. 5060
    Prev
    Next
    INDEX
    Explanations

    of

    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
    addCriterion
    -0.75
    oneof
    -0.65
     douleurs
    -0.61
     âmes
    -0.60
    InjectAttribute
    -0.60
     gynhyrchwyd
    -0.60
    ParallelGroup
    -0.58
     виправивши
    -0.58
     Professions
    -0.56
     leksikon
    -0.56
    POSITIVE LOGITS
     like
    0.57
     alike
    0.53
    })`
    0.50
     equivalent
    0.47
     equivalently
    0.46
     autant
    0.46
     lesser
    0.46
    QtCore
    0.46
     igual
    0.44
     Seperti
    0.44
    Activations Density 0.003%

    No Known Activations