© 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. 4-CLT-HP
    7. 1067
    Prev
    Next
    INDEX
    Explanations

    diagnostic

    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
    ⓧ
    -0.50
     CreateTagHelper
    -0.50
    AxisAlignment
    -0.50
    chaft
    -0.49
    ండి
    -0.49
     casts
    -0.47
    çants
    -0.47
    itename
    -0.47
    worths
    -0.47
    GEBURTSDATUM
    -0.47
    POSITIVE LOGITS
     mxArray
    0.57
     kasarigan
    0.54
    ]")]
    0.52
     المعيارى
    0.50
    ++)
    0.50
    SharedDtor
    0.50
    +:+
    0.49
     épreuves
    0.49
    ,))
    0.48
    principalTable
    0.48
    Activations Density 0.004%

    No Known Activations