© 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. 0-CLT-HP
    7. 93282
    Prev
    Next
    INDEX
    Explanations

    candidates/counterparts

    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
     purpoſe
    -0.96
     Shakspeare
    -0.94
     counterparts
    -0.92
     houſe
    -0.92
     Efq
    -0.92
     themſelves
    -0.91
     equivalents
    -0.90
     candidates
    -0.90
     becauſe
    -0.89
     Theſe
    -0.88
    POSITIVE LOGITS
    ])[
    0.62
     per
    0.52
    ))))
    0.50
     of
    0.50
     turned
    0.47
    NSMutable
    0.45
    éndole
    0.44
    offsetof
    0.44
    чего
    0.42
     lại
    0.42
    Activations Density 0.059%

    No Known Activations