© 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. 42025
    Prev
    Next
    INDEX
    Explanations

    nonsense

    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
     nonsense
    -1.02
     bullshit
    -0.90
     BS
    -0.85
     crap
    -0.84
    nonsense
    -0.80
     shit
    -0.76
    Nonsense
    -0.74
     rubbish
    -0.69
     bs
    -0.60
     SHIT
    -0.59
    POSITIVE LOGITS
     pinulongan
    0.72
     Monfieur
    0.69
     BoxFit
    0.68
    ی
    0.67
    ième
    0.66
     Cæsar
    0.66
     ejus
    0.62
     Efq
    0.61
     faſt
    0.61
    ingly
    0.60
    Activations Density 0.801%

    No Known Activations