© 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. 94858
    Prev
    Next
    INDEX
    Explanations

    scientific/technical texts

    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
    FieldNumber
    -0.56
    featureID
    -0.54
    complexContent
    -0.53
    deno
    -0.50
    écou
    -0.49
    rouvez
    -0.49
    uent
    -0.47
    FormTagHelper
    -0.47
    ouer
    -0.47
     écou
    -0.46
    POSITIVE LOGITS
    ms
    0.75
    mals
    0.73
    ########.
    0.71
    m
    0.66
    nical
    0.53
    ology
    0.52
    rungsseite
    0.51
    heits
    0.50
    nings
    0.50
    ensement
    0.50
    Activations Density 0.002%

    No Known Activations