© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 70
    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
     Either
    -0.53
    
    -0.50
    Cllr
    -0.49
    Either
    -0.45
     either
    -0.45
     跳转至
    -0.43
    elif
    -0.43
    either
    -0.42
    ئ
    -0.41
    
    -0.41
    POSITIVE LOGITS
    Personendaten
    0.67
    MLLoader
    0.64
    ỡng
    0.60
     виправивши
    0.59
    thenReturn
    0.59
     Ouverture
    0.58
    parsedMessage
    0.58
     censiti
    0.56
    ագրություններ
    0.54
    Autoritní
    0.54
    Activations Density 0.002%

    No Known Activations