© 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. 1674
    Prev
    Next
    INDEX
    Explanations

    rank

    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
     rank
    -0.84
     tag
    -0.80
     lure
    -0.73
     mark
    -0.72
     rip
    -0.72
     ring
    -0.71
     mask
    -0.65
     Rank
    -0.65
     Mask
    -0.62
    Rip
    -0.61
    POSITIVE LOGITS
    ex
    0.73
    ear
    0.69
    ers
    0.67
    ings
    0.65
    ie
    0.65
    er
    0.60
     кӀ
    0.60
    ed
    0.59
    ign
    0.57
     Shakspeare
    0.57
    Activations Density 0.224%

    No Known Activations