© 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. 4-CLT-HP
    7. 709
    Prev
    Next
    INDEX
    Explanations

    dimensions

    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
     صوتيه
    -0.65
     vectoriales
    -0.62
     floresta
    -0.59
     avoient
    -0.59
     resourceCulture
    -0.58
     feroit
    -0.55
     measles
    -0.54
     poveznice
    -0.54
     متعلقه
    -0.54
     Grecs
    -0.54
    POSITIVE LOGITS
    WriteBarrier
    0.57
     ca
    0.54
    windowFixed
    0.53
    colgroup
    0.50
    WRP
    0.49
    niczy
    0.48
     nearly
    0.47
     prop
    0.47
     Ben
    0.47
     various
    0.47
    Activations Density 0.004%

    No Known Activations