© 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. 95202
    Prev
    Next
    INDEX
    Explanations

    degradation

    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
     degradation
    -1.68
     Degradation
    -1.55
     degraded
    -1.44
    degradation
    -1.37
     degrading
    -1.28
     degrade
    -1.20
     degrad
    -1.07
     degra
    -1.01
    ets
    -0.75
     تانيه
    -0.75
    POSITIVE LOGITS
    vician
    0.50
     Dyck
    0.49
     plena
    0.47
    uously
    0.46
     idem
    0.45
    merken
    0.45
     ok
    0.45
     levar
    0.45
    ity
    0.45
     Lank
    0.43
    Activations Density 0.136%

    No Known Activations