© 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. 0-CLT-HP
    7. 41953
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     wither
    -1.15
     Wither
    -0.56
    cay
    -0.49
    GeneratedCode
    -0.48
     aportes
    -0.47
    AddHtmlAttribute
    -0.47
    Fre
    -0.46
    ΕΣ
    -0.46
    sca
    -0.46
     BrowserModule
    -0.46
    POSITIVE LOGITS
    numerusform
    0.66
     consultato
    0.65
     ISNI
    0.65
     Lordships
    0.61
     referenties
    0.60
     Baillargeon
    0.59
    Rè
    0.58
    Przypisy
    0.58
    BASEPATH
    0.58
    ChildIndex
    0.55
    Activations Density 0.146%

    No Known Activations