© 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. 1-CLT-HP
    7. 9049
    Prev
    Next
    INDEX
    Explanations

    it

    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
    expandindo
    -0.85
    UnusedPrivate
    -0.84
    ⓧ
    -0.82
    ValueStyle
    -0.79
    webElementXpaths
    -0.77
     препратки
    -0.77
     dataSnapshot
    -0.77
    存于互联网档案馆
    -0.66
    GraphicsUnit
    -0.65
    bootstrapcdn
    -0.64
    POSITIVE LOGITS
     apart
    0.75
     aside
    0.67
     back
    0.60
     across
    0.60
     around
    0.60
     forward
    0.58
     inside
    0.56
     ashore
    0.54
     farther
    0.54
     through
    0.52
    Activations Density 0.004%

    No Known Activations