© 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. 5-CLT-HP
    7. 3301
    Prev
    Next
    INDEX
    Explanations

    negative sentiment

    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
     cherchés
    -0.57
    crimin
    -0.55
    NamedQueries
    -0.54
     Manch
    -0.54
     ArrayAdapter
    -0.52
     PropertyChanged
    -0.52
    Vidite
    -0.50
    medriver
    -0.50
     Kuri
    -0.50
    empêcher
    -0.49
    POSITIVE LOGITS
    als
    0.50
    ations
    0.49
    erb
    0.48
    edig
    0.47
    ECC
    0.47
    lingo
    0.47
    antası
    0.47
    nościo
    0.47
    //
    0.46
    Scénario
    0.46
    Activations Density 0.000%

    No Known Activations