© 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. 0-CLT-HP
    7. 1328
    Prev
    Next
    INDEX
    Explanations

    scientific/medical research papers

    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
    دانشنامهٔ
    -0.59
    abestanden
    -0.58
     насељу
    -0.56
    __((
    -0.55
    ValueStyle
    -0.55
     valgt
    -0.52
     Aug
    -0.52
    sizeCache
    -0.52
    Aug
    -0.51
    AnchorStyles
    -0.51
    POSITIVE LOGITS
    ſelf
    0.62
    AÇÃO
    0.61
     Efq
    0.59
     myſelf
    0.57
     imagination
    0.57
    polation
    0.56
     hydrophilic
    0.56
    runApp
    0.55
     AppColors
    0.54
    ulative
    0.54
    Activations Density 0.080%

    No Known Activations