© 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. 5-CLT-HP
    7. 3302
    Prev
    Next
    INDEX
    Explanations

    time-related events

    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
    CppCodeGen
    -0.68
    numerusform
    -0.59
     autant
    -0.56
    SequentialGroup
    -0.55
    ίναι
    -0.54
     slutet
    -0.54
     autorytatywna
    -0.53
    StringProperty
    -0.53
    Referências
    -0.52
     ją
    -0.52
    POSITIVE LOGITS
     you
    0.97
     we
    0.81
     myſelf
    0.68
     I
    0.68
     consumers
    0.67
     pleaſure
    0.66
     raiſ
    0.60
     travellers
    0.60
    ^(@)
    0.60
     children
    0.59
    Activations Density 0.001%

    No Known Activations