© 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. 96733
    Prev
    Next
    INDEX
    Explanations

    with

    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
     delivering
    -0.55
     owning
    -0.54
     trying
    -0.54
     making
    -0.54
     giving
    -0.53
     enjoying
    -0.51
     robbing
    -0.51
     getting
    -0.51
     &
    -0.49
     having
    -0.49
    POSITIVE LOGITS
     متعلقه
    0.63
    帖最后由
    0.63
    ]--;
    0.62
     purpoſe
    0.60
     researchers
    0.60
    ricians
    0.60
     unknownFields
    0.59
     myſelf
    0.59
    ViewImports
    0.58
     collaborators
    0.57
    Activations Density 0.002%

    No Known Activations