© 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. 93826
    Prev
    Next
    INDEX
    Explanations

    chemical processes/studies

    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
    s
    -0.64
     eliminating
    -0.59
     refusé
    -0.58
    Elimin
    -0.57
    insula
    -0.57
     inconvénients
    -0.56
     élimin
    -0.56
    .;
    -0.55
     capuche
    -0.51
    ed
    -0.50
    POSITIVE LOGITS
     itſelf
    0.88
     ſtate
    0.83
     purpoſe
    0.82
     Majefty
    0.80
     ſte
    0.78
     pleaſure
    0.78
     Efq
    0.75
     ſta
    0.74
    ſelf
    0.73
     juſ
    0.73
    Activations Density 0.061%

    No Known Activations