© 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. 5-CLT-HP
    7. 4704
    Prev
    Next
    INDEX
    Explanations

    severe

    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
     kasarigan
    -0.94
     صوتيه
    -0.88
    oustics
    -0.73
    +#+#
    -0.70
     tended
    -0.67
     estekak
    -0.62
     seemed
    -0.61
     refusé
    -0.61
    はじめに
    -0.60
    évaluateur
    -0.60
    POSITIVE LOGITS
    GenerationType
    0.48
     pathlib
    0.44
     dure
    0.41
     rallies
    0.40
    demia
    0.40
     lhes
    0.39
    posedge
    0.38
    Географиясе
    0.38
    ling
    0.37
    CommonModule
    0.37
    Activations Density 0.040%

    No Known Activations