© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10930
    Prev
    Next
    INDEX
    Explanations

    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
     baits
    -0.62
     favours
    -0.57
     waivers
    -0.56
     Vial
    -0.54
    Skocz
    -0.53
     cheques
    -0.52
     alternates
    -0.52
     motives
    -0.52
     stubs
    -0.52
     verdicts
    -0.52
    POSITIVE LOGITS
     the
    0.64
    CrossRef
    0.56
     a
    0.55
    ipedi
    0.54
     estekak
    0.53
     مرئيه
    0.53
    sst
    0.52
    getFullYear
    0.52
    原始内容存档于
    0.52
     an
    0.52
    Activations Density 0.067%

    No Known Activations