© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 969
    Prev
    Next
    INDEX
    Explanations

    the

    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
    tvguidetime
    -0.66
    ValueStyle
    -0.60
    XtraReports
    -0.57
    ButterKnife
    -0.55
    AutoScale
    -0.53
     diaper
    -0.52
    Tikang
    -0.50
    COLOUR
    -0.49
     fameux
    -0.48
     squishy
    -0.48
    POSITIVE LOGITS
     Nation
    0.60
     ?>>
    0.54
    irot
    0.52
     President
    0.51
     Secretary
    0.50
    WithMany
    0.49
    oustics
    0.48
    ibatis
    0.48
    ="#">
    0.48
    ской
    0.46
    Activations Density 0.010%

    No Known Activations