© 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. 0-CLT-HP
    7. 43365
    Prev
    Next
    INDEX
    Explanations

    research studies

    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
    WebVitals
    -0.83
    meant
    -0.75
     meant
    -0.72
     intended
    -0.65
    WriteBarrier
    -0.64
     Intended
    -0.64
    CppMethod
    -0.62
     متعلقه
    -0.60
    intended
    -0.60
     goutte
    -0.59
    POSITIVE LOGITS
     the
    1.02
     a
    0.79
     "
    0.67
    irability
    0.67
     some
    0.66
     “
    0.65
     it
    0.64
     someone
    0.64
     an
    0.63
     to
    0.63
    Activations Density 0.024%

    No Known Activations