© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74972
    Prev
    Next
    INDEX
    Explanations

    Various types of updates

    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
    ftagPool
    -1.05
     MenuView
    -0.74
    InputBorder
    -0.67
    webElement
    -0.67
    AddTagHelper
    -0.65
    ngrx
    -0.65
    المشاركات
    -0.65
    fjspx
    -0.64
    complexContent
    -0.64
     createSlice
    -0.60
    POSITIVE LOGITS
     décro
    0.52
     being
    0.50
     vapeur
    0.45
    being
    0.44
     menengah
    0.43
    日在
    0.42
    
    0.41
     BEING
    0.41
    entibus
    0.41
     boire
    0.41
    Activations Density 0.000%

    No Known Activations