© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12450
    Prev
    Next
    INDEX
    Explanations

    lamps

    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
    matchCondition
    -1.06
    NameInMap
    -1.05
    Geplaatst
    -0.95
    expandindo
    -0.92
    AnimationsModule
    -0.85
    tagHelperRunner
    -0.84
    脚注の使い方
    -0.82
     يتيمه
    -0.81
    \{\\
    -0.79
    UserScript
    -0.79
    POSITIVE LOGITS
    s
    0.54
     bien
    0.44
    <0xE2>
    0.43
    /-/
    0.41
     self
    0.41
     surface
    0.40
    舊
    0.40
    перь
    0.40
     fin
    0.39
    bjerg
    0.39
    Activations Density 0.058%

    No Known Activations