© 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. 41330
    Prev
    Next
    INDEX
    Explanations

    Aqu

    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
     Efq
    -1.02
     Shakspeare
    -0.85
    keeping
    -0.84
     Majefty
    -0.83
    ſelves
    -0.79
     fevere
    -0.79
     Houſe
    -0.75
     Diſ
    -0.75
     Chriftian
    -0.72
     Daphne
    -0.70
    POSITIVE LOGITS
    s
    0.72
     autorytatywna
    0.51
     doInBackground
    0.51
     kasarigan
    0.45
    sau
    0.43
    sin
    0.41
    h
    0.40
    duff
    0.40
    طلق
    0.40
    r
    0.40
    Activations Density 0.161%

    No Known Activations