© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43236
    Prev
    Next
    INDEX
    Explanations

    "{"

    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
     myſelf
    -0.90
     Theſe
    -0.88
    ^(@)
    -0.84
     theſe
    -0.82
     themſelves
    -0.82
     ſeveral
    -0.81
     ſtill
    -0.78
     ſame
    -0.75
     firſt
    -0.75
     becauſe
    -0.75
    POSITIVE LOGITS
     sunt
    0.50
    язы
    0.50
     se
    0.49
    huriyet
    0.47
     sitesinde
    0.43
    ric
    0.41
     xảy
    0.41
     itinéraires
    0.40
    Handlung
    0.39
    ))
    0.39
    Activations Density 1.883%

    No Known Activations