© 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. 4-CLT-HP
    7. 978
    Prev
    Next
    INDEX
    Explanations

    render

    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
     насељу
    -0.54
    basicConfig
    -0.50
     дописавши
    -0.49
    BASELINE
    -0.47
    AndEndTag
    -0.47
    bootstrapcdn
    -0.47
    змом
    -0.47
    Erreferentziak
    -0.47
    ATIVES
    -0.47
    ंदीखरीदारी
    -0.45
    POSITIVE LOGITS
     aid
    0.71
     assistance
    0.71
     unto
    0.70
     help
    0.67
     VizieR
    0.63
     Walkover
    0.62
     ayuda
    0.61
     service
    0.61
     ajuda
    0.59
    assistance
    0.59
    Activations Density 0.006%

    No Known Activations