© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1361
    Prev
    Next
    INDEX
    Explanations

    cyc

    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
    ///</
    -0.49
     begin
    -0.48
    vind
    -0.48
     jour
    -0.47
    STORY
    -0.44
    zional
    -0.43
     calendriers
    -0.42
    ]]
    -0.42
    vrons
    -0.42
    zelf
    -0.41
    POSITIVE LOGITS
    loem
    0.64
     propOrder
    0.59
    eavour
    0.56
    ImageContext
    0.56
     IBOutlet
    0.56
     StringTokenizer
    0.53
     Units
    0.53
    ately
    0.52
    kloped
    0.52
     Configuration
    0.51
    Activations Density 0.034%

    No Known Activations