© 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. 42536
    Prev
    Next
    INDEX
    Explanations

    Jah

    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
     silt
    -0.71
     propOrder
    -0.68
    e
    -0.58
     NUKAT
    -0.57
    acrylamide
    -0.55
    avir
    -0.54
    erai
    -0.54
    lek
    -0.53
     början
    -0.53
    i
    -0.53
    POSITIVE LOGITS
     autorytatywna
    0.84
     препратки
    0.59
     geslacht
    0.52
     ddelweddau
    0.52
     للمعارف
    0.51
    .*")]
    0.51
    fulness
    0.49
    ostante
    0.47
    VideoCapture
    0.47
     GetEnumerator
    0.47
    Activations Density 0.142%

    No Known Activations