© 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. 79
    Prev
    Next
    INDEX
    Explanations

    gl

    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
    AsUp
    -0.58
    lü
    -0.49
    으로
    -0.48
     للمعارف
    -0.45
    lude
    -0.45
    ]=>
    -0.44
    lge
    -0.44
     Loew
    -0.42
    AutoScaleMode
    -0.41
     EClass
    -0.40
    POSITIVE LOGITS
    TargetException
    0.65
     محفوظة
    0.64
    ateral
    0.60
    ibrill
    0.59
    ibrary
    0.58
    TagHelper
    0.57
    istice
    0.54
    ={`/
    0.54
    INK
    0.54
    derry
    0.54
    Activations Density 0.010%

    No Known Activations