© 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. 13795
    Prev
    Next
    INDEX
    Explanations

    Hong

    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
    Hong
    -0.86
     Hong
    -0.80
     hong
    -0.65
    InstrumentedTest
    -0.65
     Directorate
    -0.64
    hong
    -0.63
    NameInMap
    -0.54
     ProtoMessage
    -0.52
     Autorisations
    -0.50
    Cyfeiriadau
    -0.49
    POSITIVE LOGITS
    ViewFeatures
    0.79
    ongiorno
    0.62
    anguages
    0.61
     rapides
    0.58
     Turquie
    0.57
    actionMode
    0.57
    gridx
    0.54
    GZIP
    0.54
    strix
    0.53
    󠁢
    0.53
    Activations Density 0.006%

    No Known Activations