© 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. 92459
    Prev
    Next
    INDEX
    Explanations

    of

    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
     виправивши
    -1.02
     itſelf
    -0.95
     myſelf
    -0.93
    ſelves
    -0.92
    ^(@)
    -0.90
    ſelf
    -0.89
     Efq
    -0.87
     hâte
    -0.85
     auffi
    -0.85
    σθαι
    -0.80
    POSITIVE LOGITS
     this
    0.64
     it
    0.62
    ...
    0.57
    X
    0.50
     was
    0.49
    alo
    0.49
    Is
    0.49
    ....
    0.49
    이
    0.48
    it
    0.48
    Activations Density 0.000%

    No Known Activations