© 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. 5-CLT-HP
    7. 497
    Prev
    Next
    INDEX
    Explanations

    viewed

    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
     the
    -0.67
    SequentialGroup
    -0.65
     a
    -0.59
     EconPapers
    -0.59
    ulex
    -0.58
     springfox
    -0.55
    GV
    -0.55
    ampton
    -0.54
    marvin
    -0.53
    acana
    -0.52
    POSITIVE LOGITS
     as
    0.75
     mathematically
    0.68
    มาะ
    0.57
     conceptually
    0.53
     mechanically
    0.53
     >=",
    0.52
     descended
    0.52
    rozum
    0.51
     estekak
    0.50
    ApiModel
    0.50
    Activations Density 0.000%

    No Known Activations