© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 345
    Prev
    Next
    INDEX
    Explanations

    Legal/official contexts

    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
    GraphicsUnit
    -0.56
     PeEnEo
    -0.54
     '\\;'
    -0.52
    wpi
    -0.49
     Gegenteil
    -0.47
    出版年
    -0.47
     proté
    -0.47
     nakalista
    -0.47
     mxArray
    -0.47
    neous
    -0.46
    POSITIVE LOGITS
    MergeFrom
    0.69
    دانشنامهٔ
    0.57
    MotionEvent
    0.56
     adeno
    0.55
     برانيه
    0.54
     isInitialized
    0.54
     protoimpl
    0.53
    NSNotification
    0.52
     onCancelled
    0.52
    modelBuilder
    0.51
    Activations Density 0.003%

    No Known Activations