© 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. 5-CLT-HP
    7. 97948
    Prev
    Next
    INDEX
    Explanations

    only

    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
     genoux
    -0.49
     épaules
    -0.49
     låg
    -0.48
     lèvres
    -0.48
     dessutom
    -0.45
     mauvaises
    -0.43
     pudieran
    -0.43
     intérêts
    -0.42
     vitesses
    -0.42
     vœux
    -0.42
    POSITIVE LOGITS
     things
    0.92
     signs
    0.92
     exceptions
    0.91
     ways
    0.88
     links
    0.84
     clues
    0.83
    things
    0.81
     similarities
    0.79
     alternatives
    0.79
    THINGS
    0.79
    Activations Density 0.003%

    No Known Activations