© 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. 20-CLT-HP
    7. 75802
    Prev
    Next
    INDEX
    Explanations

    science/names

    np_max-act-logits · 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
     виправивши
    -0.59
    קישורים
    -0.58
     crossorigin
    -0.58
     للمعارف
    -0.52
    DebuggerNonUser
    -0.51
    /**
    -0.50
     Baruch
    -0.50
    ContextCompat
    -0.50
    WindowEvent
    -0.50
    ]<<"
    -0.50
    POSITIVE LOGITS
     Wikispecies
    0.48
    icola
    0.48
    IUrlHelper
    0.48
    ocera
    0.48
    irability
    0.47
    opra
    0.46
    ifolium
    0.45
    icles
    0.44
    opsis
    0.43
    ICIA
    0.42
    Activations Density 0.001%

    No Known Activations