© 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. 5-CLT-HP
    7. 97229
    Prev
    Next
    INDEX
    Explanations

    learning and new information

    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
    setMode
    -0.47
     to
    -0.45
    okkal
    -0.45
     nghi
    -0.45
    Mode
    -0.45
     Mode
    -0.44
     mode
    -0.44
     
    -0.43
    .
    -0.42
    মা
    -0.41
    POSITIVE LOGITS
    ViewFeatures
    1.05
    AddTagHelper
    1.02
    LookAnd
    0.94
    featureID
    0.90
    setVerticalGroup
    0.89
    HasAnnotation
    0.87
     EClass
    0.85
    脚注の使い方
    0.81
    webElementXpaths
    0.80
    AnchorStyles
    0.79
    Activations Density 0.002%

    No Known Activations